State monitoring method and system for field equipment in control system

Abstract

The invention discloses a state monitoring method and system for field equipment in a control system, and relates to the technical field of equipment monitoring, and the method comprises the steps: building a digital twin model related to the field equipment based on the first related data of the field equipment; the first related data comprises static data, historical operation environment data and historical dynamic response behavior data of the field equipment; acquiring second related data of the field device, and comparing and analyzing the second related data with the expected behavior of the digital twinborn model; and based on a comparative analysis result, performing fault identification on the field equipment, and completing state monitoring of the field equipment in the control system. According to the invention, multi-source data are integrated, and the monitoring comprehensiveness and accuracy are improved; through a digital twinning technology, virtual and real combined dynamic monitoring is realized, and the real-time performance and adaptability of the system are enhanced. Meanwhile, through comparative analysis and intelligent identification, the fault prediction and prevention capability is improved, and the effect and efficiency of field equipment state monitoring are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment monitoring, and in particular to a method and system for monitoring the status of field equipment in a control system. Background Art

[0002] In thermal power units, the essence of equipment condition monitoring and diagnosis is the pattern recognition of equipment operating status. Whether it is the residual life assessment of equipment in fault prediction and health management, or the equipment performance degradation assessment and prediction in intelligent maintenance, the essence is to identify the current operating status of the equipment through the analysis of equipment data, and predict the status trend, so as to take corresponding measures before the equipment performance reaches an unacceptable state to avoid unexpected failures. There are two types of faults in the use of sensors and actuators, one is a hard fault in which the device is completely damaged, and the other is a soft fault in which the device performance deteriorates. In the early condition monitoring and fault diagnosis, only regular inspections by relevant personnel can improve their safety and reliability. The regular inspection method can only detect their physical damage, but not their internal faults; regular inspections have high requirements for environmental safety, which has great limitations. With the development of computer technology and communication technology, sensor and actuator fault diagnosis is developing in the direction of informatization and internalization, that is, internal faults are diagnosed by analyzing and processing sensor and actuator signals.

[0003] First, traditional models cannot fully reflect the characteristics of equipment, and it is difficult to simultaneously consider the physical characteristics and operating environment of field equipment and capture the dynamic characteristics of equipment. Second, existing technologies often use fixed thresholds or static models, which are difficult to adapt to the dynamic changes in equipment performance, timely detect minor changes in equipment status, and distinguish between normal performance fluctuations and abnormal conditions. In addition, traditional condition monitoring is often passive and mainly focuses on faults that have already occurred. It has insufficient predictive capabilities and is difficult to provide specific types and severity of faults. Summary of the invention

[0004] In view of the problems existing in the state monitoring method of field devices in the existing control system, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is how to provide a method for monitoring the status of field equipment in a control system.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present invention provides a state monitoring method for field equipment in a control system, which includes constructing a digital twin model about the field equipment based on first relevant data of the field equipment; the first relevant data includes static data, historical operating environment data and historical dynamic response behavior data of the field equipment; the digital twin model includes a three-dimensional model, an operating environment model and a dynamic behavior model; obtaining second relevant data of the field equipment, and comparing and analyzing the second relevant data with the expected behavior of the digital twin model; based on the comparison and analysis results, identifying faults of the field equipment to complete the state monitoring of the field equipment in the control system.

[0008] As a preferred scheme of the state monitoring method of field equipment in the control system described in the present invention, wherein: the field equipment includes sensors and actuators; the construction process of the digital twin model includes the following steps: establishing a three-dimensional model of the field equipment according to the static data of the field equipment; the static data includes geometric data, material data and structural data; establishing an operating environment model of the field equipment according to historical operating environment data; the historical operating environment data includes ambient temperature, ambient humidity and ambient pressure; establishing a dynamic behavior model of the field equipment according to historical dynamic response behavior data; integrating the three-dimensional model, operating environment model and dynamic behavior model of the field equipment into a digital twin model of the field equipment; and mapping the field equipment and the operating environment where the field equipment is located to the virtual space in real time through the digital twin model of the field equipment.

[0009] As a preferred solution of the state monitoring method of field equipment in the control system described in the present invention, wherein: a three-dimensional model of the field equipment is established according to the static data of the field equipment, including the following steps: constructing a three-dimensional geometric domain V based on the three-dimensional geometric shape of the field equipment; discretizing the three-dimensional geometric domain V into multiple units; combining the shape function matrix N, the material stiffness matrix D determined by the material data, and the shape function derivative matrix B determined by the structural data to obtain the response of each unit; performing multiple integral accumulation on the response of each unit in the three-dimensional geometric domain V to obtain the total response of the three-dimensional geometric domain V, that is, the three-dimensional model M1. An operating environment model of the field equipment is established according to historical operating environment data, including the following steps: constructing an environmental temperature model according to historical environmental temperature data, and performing nonlinear mapping on the historical environmental temperature data through the environmental temperature model; constructing an environmental humidity model according to historical environmental humidity data, and performing nonlinear mapping on the historical environmental humidity data through the environmental humidity model; constructing an environmental pressure model according to historical environmental pressure data, and performing nonlinear mapping on the historical environmental pressure data through the environmental pressure model; obtaining a comprehensive nonlinear mapping model according to the environmental temperature model, the environmental humidity model and the environmental pressure model; introducing a comprehensive weight factor, and constructing the operating environment model of the field equipment in combination with the comprehensive nonlinear mapping model; wherein the comprehensive weight factor refers to the comprehensive weight of combining historical environmental temperature data, historical environmental humidity data and historical environmental pressure data, and the comprehensive influence of different environmental parameters on the operating status of the equipment is obtained through the comprehensive weight factor.

[0010] As a preferred solution of the state monitoring method of field equipment in the control system described in the present invention, the historical dynamic response behavior data includes the historical time response, historical measurement accuracy, historical vibration data, historical accumulated operating time, and historical current consumption of the field equipment.

[0011] A dynamic behavior model of the field device is established based on historical dynamic response behavior data, including the following steps: determining performance indicators for monitoring the dynamic behavior of the field device based on historical time response, historical measurement accuracy and historical vibration data of the field device; determining degradation factors of the field device based on historical accumulated operating time and historical current consumption of the field device; and obtaining the dynamic behavior model of the field device by combining the performance indicators and degradation factors.

[0012] As a preferred solution of the state monitoring method of field equipment in the control system of the present invention, the formula of the digital twin model of the field equipment is:

[0013]

[0014] Among them, M(t) is the digital twin model output of the field equipment at time t; Ω is the parameterized geometric domain; J(x, t) is the Jacobi transformation factor; M1 is the three-dimensional model of the field equipment; M2(t) is the dynamic behavior model of the field equipment that changes with time; M3 is the operating environment model; It is a comprehensive coupling function of three-dimensional model, dynamic behavior model and operating environment model.

[0015] As a preferred solution of the method for monitoring the status of field equipment in the control system of the present invention, the second related data refers to the operating environment data and dynamic response behavior data collected in real time.

[0016] Comparing and analyzing the second relevant data with the expected behavior of the digital twin model includes the following steps: acquiring the second relevant data I(t) in real time; combining the second relevant data and the static data, and using the digital twin model M(t) to calculate the expected behavior output Y(t) of the field device:

[0017]

[0018] Among them, M2(I E (t)) is based on real-time operating environment data I E (t) operating environment model; M3(I D (t)) is based on real-time dynamic response behavior data I D (t) dynamic behavior model.

[0019] The actual observed data X(t) is obtained; and the difference Z(t) between the expected behavior output Y(t) and the actual observed data X(t) is calculated, that is, the comparative analysis result.

[0020] As a preferred solution of the state monitoring method of field equipment in the control system described in the present invention, wherein: if Z(t) is always equal to the actual observed value X(t), that is, the expected behavior output Y(t) is always zero or a fixed value, or Z(t) jumps to a preset multiple exceeding the normal fluctuation range within a preset time, or Z(t) presents a completely random pattern and no longer has any correlation with the system input or other related variables, and continues to exist until exceeding the preset time threshold, then the field device is determined to be in a hard fault state of complete damage; if the absolute value of Z(t) shows an upward trend in the past N time units, and the increase exceeds the preset threshold A, then the field device is determined to be in a soft fault state with deteriorated performance; if the standard deviation of Z(t) increases by more than the preset threshold B in the past M time units, then the field device is determined to be in a soft fault state with deteriorated performance; if the spectrum analysis of Z(t) shows that the energy increase in a specific frequency range exceeds the preset threshold C, then the field device is determined to be in a soft fault state with deteriorated performance.

[0021] In the second aspect, an embodiment of the present invention provides a status monitoring system for field equipment in a control system, comprising: a model building module, used to build a digital twin model about the field equipment based on the first relevant data of the field equipment; an acquisition and analysis module, used to obtain the second relevant data of the field equipment, and compare and analyze the second relevant data with the expected behavior of the digital twin model; an identification and monitoring module, used to identify faults of the field equipment based on the comparison and analysis results, and complete the status monitoring of the field equipment in the control system.

[0022] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, any step of the above-mentioned method for status monitoring of field equipment in a control system is implemented.

[0023] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the above-mentioned method for status monitoring of field equipment in a control system is implemented.

[0024] The beneficial effects of the present invention are as follows: First, the digital twin model constructed by the present invention not only takes into account the static characteristics of the equipment, but also includes historical operating environment data and dynamic response behavior data, so as to more accurately reflect the overall status of the equipment. Secondly, by obtaining the second relevant data of the equipment and comparing and analyzing it with the expected behavior of the digital twin model, real-time and dynamic status monitoring is achieved, adapting to the dynamic changes in equipment performance, and overcoming the limitations of traditional fixed models. Finally, fault identification is performed based on the results of comparative analysis, which can not only diagnose existing faults, but also has the ability to predict potential faults, thus realizing preventive maintenance. The present invention integrates multi-source data to improve the comprehensiveness and accuracy of monitoring; through digital twin technology, dynamic monitoring combining virtual and real is realized, and the real-time and adaptability of the system are enhanced; at the same time, through comparative analysis and intelligent identification, the fault prediction and prevention capabilities are improved, greatly improving the effect and efficiency of equipment status monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0026] Figure 1 It is an overall flow chart of the state monitoring method of field equipment in the control system of the present invention.

[0027] Figure 2 A computer device diagram of the method for monitoring the status of field devices in a control system of the present invention. DETAILED DESCRIPTION

[0028] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0029] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0030] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0031] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0032] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0033] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0034] Example 1

[0035] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a method for monitoring the status of field equipment in a control system.

[0036] In the related technologies, firstly, the traditional models cannot fully reflect the characteristics of the equipment, and it is difficult to simultaneously consider the physical characteristics and operating environment of the field equipment and capture the dynamic characteristics of the equipment. Secondly, the existing technologies often use fixed thresholds or static models, which are difficult to adapt to the dynamic changes in equipment performance, timely detect minor changes in equipment status, and distinguish between normal performance fluctuations and abnormal conditions. In addition, traditional condition monitoring is often passive and mainly focuses on faults that have already occurred. It has insufficient predictive capabilities and is difficult to provide the specific type and severity of the fault.

[0037] The present application provides a method for effectively solving the above-mentioned problems. Next, a method for implementing a state monitoring method of a field device in the control system will be described in detail in combination with multiple embodiments.

[0038] Figure 1 A method and a method flow chart of a state monitoring method of a field device in a control system are shown, comprising the following steps:

[0039] S1: Construct a digital twin model of the field device based on first relevant data of the field device.

[0040] S2: Obtain second relevant data of the field equipment, and compare and analyze the second relevant data with the expected behavior of the digital twin model.

[0041] S3: Based on the comparative analysis results, fault identification is performed on the field equipment to complete the status monitoring of the field equipment in the control system.

[0042] Next, each step is introduced in detail.

[0043] S1: Construct a digital twin model of the field device based on first relevant data of the field device.

[0044] Specifically, in this embodiment, the field device includes a sensor and an actuator. The first related data includes static data, historical operating environment data, and historical dynamic response behavior data of the field device. The digital twin model includes a three-dimensional model, an operating environment model, and a dynamic behavior model.

[0045] S1.1: Establish a three-dimensional model of the field equipment according to the static data of the field equipment, wherein the static data of the field equipment includes geometric data, material data and structural data.

[0046] Specifically, based on the three-dimensional geometric shape of the field equipment, a corresponding three-dimensional geometric domain V is constructed in the computer, and the finite element method is used in this three-dimensional geometric domain to discretize the entire area into many units. The response on each unit can be expressed as the transpose of the shape function matrix N, multiplied by the material stiffness matrix D determined by the material data, and then multiplied by the shape function derivative matrix B determined by the structural data. In order to obtain the total response of the entire three-dimensional geometric domain V, it is necessary to perform triple integral accumulation of the response of each unit in the entire three-dimensional geometric domain V, that is, volume integral operation Finally, the overall static response M1 of the field equipment under given material, geometry and structural data is obtained, thus establishing the basis for building a digital twin model of the field equipment.

[0047] The three-dimensional model M1 of the field equipment is expressed by the following formula:

[0048]

[0049] Among them, V is the geometric domain of the 3D model, that is, the 3D space area occupied by the 3D model; N is the shape function matrix, which is determined by the interpolation method; D is the material stiffness matrix, which is determined by the material data; B is the shape function derivative matrix, which is determined by the geometric data and structural data; N T is the transpose of the shape function matrix, which is n×1, where n is the number of element nodes.

[0050] The formula compactly summarizes the digital modeling process of finite element discretization, material behavior, geometric influence, etc., and is an extremely important mathematical description in digital twin technology. By solving this formula, a virtual model consistent with the static characteristics of the on-site equipment can be efficiently constructed.

[0051] S1.2: Establish an operating environment model of the field equipment based on historical operating environment data, wherein the historical operating environment data includes ambient temperature, ambient humidity and ambient pressure.

[0052] The accuracy of monitoring the operating environment of thermal power plant equipment is a key issue. The linear model in the prior art cannot capture subtle changes in environmental parameters, resulting in inaccurate monitoring results. The present invention can capture subtle changes in environmental parameters by introducing the Gaussian kernel function; through the design of comprehensive weight factors, it can reasonably reflect the comprehensive influence of multiple parameters; through integral operations, the stability and accuracy of the model are improved. In practical applications, these improvements can effectively predict the operating status of the equipment, discover potential problems in a timely manner, and avoid equipment failures due to environmental changes, thereby improving the reliability and safety of the equipment.

[0053] Specifically, the steps of constructing the operating environment model are: constructing an ambient temperature model based on historical ambient temperature data, and performing nonlinear mapping on the historical ambient temperature data through the ambient temperature model. T (T t ,T t-1 ) is as follows:

[0054]

[0055] Among them, T t is the ambient temperature at time t; T t-1 is the ambient temperature at time t-1; σ T is the scale parameter of the temperature Gaussian kernel function.

[0056] The environmental humidity model is constructed based on the historical environmental humidity data, and the historical environmental humidity data is nonlinearly mapped through the environmental humidity model. Environmental humidity model K H (H t ,H t-1 ) is as follows:

[0057]

[0058] Among them, H t is the ambient humidity at time t; H t-1 is the ambient humidity at time; σ H is the scale parameter of the humidity Gaussian kernel function.

[0059] An environmental pressure model is constructed based on historical environmental pressure data, and nonlinear mapping of historical environmental pressure data is performed through the environmental pressure model. Environmental pressure model K P (P t ,P t-1 ) is as follows:

[0060]

[0061] Among them, P t is the environmental pressure at time t; Pt-1 is the ambient pressure at time t-1; σ P is the scale parameter of the pressure Gaussian kernel function.

[0062] According to the environmental temperature model, environmental humidity model and environmental pressure model, a comprehensive nonlinear mapping model is obtained. Comprehensive nonlinear mapping model K THP The specific formula is:

[0063] K THP =K T (T t ,T t-1 )+K H (H t ,H t-1 )+K P (P t ,P t-1 ).

[0064] It should be noted that due to the complexity and variability of the operating environment of thermal power units, the model is required to capture subtle changes in environmental parameters, and the Gaussian kernel function has good nonlinear mapping capabilities, which is suitable for handling this situation. Compared with the linear model, the Gaussian kernel function can more accurately reflect the complex changes in temperature, humidity and pressure data. Therefore, in this embodiment, the Gaussian kernel function is used to perform nonlinear mapping on historical environmental humidity data, historical environmental pressure data and historical environmental temperature data.

[0065] Introduce the comprehensive weight factor J(T,H,P,t) and combine it with the comprehensive nonlinear mapping model K THP , construct the operating environment model of the field equipment. The specific formula of the operating environment model M2(t) is:

[0066]

[0067] Preferably, different environmental parameters have different degrees of influence on field equipment. By introducing a comprehensive weight factor, the influence weight of each parameter can be reasonably reflected, so that the model can flexibly adjust the contribution of temperature, humidity and pressure to the operating status, thereby improving the accuracy and robustness of the model.

[0068] Furthermore, the fully expanded formula of the operating environment model M2(t) is expressed as:

[0069]

[0070] Among them, T is the ambient temperature, and changes in ambient temperature will affect the working state of the field equipment; H is the ambient humidity, and changes in ambient humidity will also affect the field equipment, especially the corrosion and aging of the field equipment; P is the ambient pressure, and changes in ambient pressure will affect the performance and stability of the field equipment; t is time, and the dynamic changes of environmental parameters can be tracked through changes in time; σ T is the scale parameter of the temperature Gaussian kernel function, through which the influence of temperature change can be adjusted; σ H is the scale parameter of the humidity Gaussian kernel function, through which the influence of humidity changes can be adjusted; σ P is the scale parameter of the pressure Gaussian kernel function, through which the influence of pressure change can be adjusted; Ω is the integration domain; J(T,H,P,t) is the comprehensive weight factor, and the specific expression is:

[0071] J(T,H,P,t)=α T T t +α H H t +α P P t ;

[0072] Among them, α T is the temperature weight coefficient, α H is the humidity weight coefficient, α P It should be noted that, in this embodiment, by introducing a comprehensive weight factor, the comprehensive impact of ambient temperature, humidity and pressure on the operating environment of the field equipment is more reasonably reflected.

[0073] S1.3: Construct a dynamic behavior model of the field equipment based on historical dynamic response behavior data.

[0074] The historical dynamic response behavior data includes the historical time response, historical measurement accuracy, historical vibration data, historical accumulated operating time, and historical current consumption of the field equipment.

[0075] In a preferred embodiment, these historical dynamic response behavior data can fully capture the dynamic characteristics of the equipment. By collecting and analyzing multi-dimensional historical data such as historical time response, measurement accuracy, vibration data, cumulative operating time and current consumption, a more comprehensive and accurate dynamic behavior model can be constructed. This multi-dimensional data acquisition enables the model to better reflect the dynamic characteristics of the equipment under different working conditions, thereby improving the accuracy and reliability of monitoring. Traditional fixed thresholds or static models are difficult to capture changes in equipment performance over time, while dynamic behavior models based on historical dynamic response behavior data can be continuously updated and optimized as new data accumulates, thereby better adapting to dynamic changes in equipment performance. This enables the system to promptly detect subtle changes in equipment status and distinguish between normal performance fluctuations and abnormal conditions.

[0076] In addition, the dynamic behavior model provides rich input data for the digital twin model. In the present invention, these historical dynamic response behavior data are the basis for building the dynamic behavior model. When the dynamic behavior model, the three-dimensional model and the operating environment model are integrated, a more comprehensive and accurate digital twin model can be formed. This integrated model can simultaneously consider the physical characteristics, operating environment and dynamic behavior of the equipment, so as to better simulate and predict the actual operating status of the equipment.

[0077] Based on the historical time response of field devices Historical measurement accuracy and historical vibration data Determine performance indicators for monitoring the dynamic behavior of field equipment:

[0078]

[0079] Based on the historical cumulative operating time of field equipment and historical current consumption Determine the degradation factors of field equipment:

[0080]

[0081] Combining the performance indicators and degradation factors, the dynamic behavior model M3 of the field equipment is obtained:

[0082]

[0083] Where t is the current time; t opt is the optimal response time; τ is the time constant, indicating the system response speed; x is the measured value; μ is the true value or expected value; σ is the standard deviation, indicating the measurement uncertainty; f is the current vibration frequency; f cis the characteristic vibration frequency or normal working frequency; L is the current accumulated running time; L0 is the benchmark running time, which can be the expected life span or maintenance cycle of the equipment; I is the current current consumption; I nom is the rated current consumption; I max is the maximum allowable current consumption.

[0084] S1.4: Integrate the three-dimensional model, operating environment model and dynamic behavior model of the field equipment into a digital twin model of the field equipment.

[0085] Specifically, the digital twin model of the field equipment is expressed by the following formula:

[0086]

[0087] Among them, M(t) is the complete digital twin model output of the field equipment at time t; Ω is the parameterized geometric domain, which represents the geometric space range of the physical system described by the model; J(x, t) is the Jacobi transformation factor, which is used for coordinate mapping transformation; M1 is the three-dimensional model of the field equipment; M2(t) is the operating environment model; M3 is the dynamic behavior model; To synthesize the coupling function, the three sub-models (3D model, dynamic behavior model, and operating environment model) are nonlinearly coupled to form a complete digital twin model output; It is a comprehensive coupling function of three-dimensional model, dynamic behavior model and operating environment model.

[0088] S1.5: Map the field device and the operating environment of the field device to the virtual space in real time through the digital twin model of the field device.

[0089] Preferably, the present invention realizes accurate state monitoring of sensors and actuators by constructing a digital twin model of field equipment, greatly improving fault diagnosis capabilities and predictive maintenance levels. For example, it can simultaneously analyze multiple parameters such as the position, stem force and flow of the control valve, and quickly identify problems such as jamming or leakage. By tracking the usage history and performance changes of the equipment, the digital twin model provides a reliable basis for formulating personalized calibration and maintenance plans, such as predicting the optimal calibration time based on the historical performance data of the flow meter. In addition, it can also assist in the optimization of control strategies, such as testing the impact of different PID parameters on the boiler combustion control system in a virtual environment. In terms of equipment selection and update decisions, long-term accumulated operating data helps to more accurately evaluate the performance of different products under actual working conditions. It is worth noting that the digital twin model also enhances network security protection capabilities and can identify abnormal data fluctuations that may be caused by network attacks. Finally, it provides operators with a realistic virtual training environment, effectively improving training results and reducing human errors in actual operations. In general, the application of digital twin technology in the control system of thermal power units not only improves equipment reliability and system stability, but also provides strong support for equipment management, control optimization, personnel training and other aspects. It is a key technology to improve the overall operational efficiency and safety of thermal power plants.

[0090] Step S2: Obtain second relevant data of the field equipment, and compare and analyze the second relevant data with the expected behavior of the digital twin model.

[0091] It should be noted that the second related data is specifically historical operating environment data and historical dynamic response behavior data collected in real time.

[0092] S2.1: Acquire the second relevant data I(t) in real time.

[0093] S2.2: Combine the second related data and static data and use the digital twin model M(t) to calculate the expected behavior output of the field equipment:

[0094]

[0095] S2.3: Obtain actual observation data X(t).

[0096] S2.4: Calculate the difference between the expected behavior output Y(t) and the actual observed data X(t):

[0097] Z(t)=||X(t)-Y(t)||;

[0098] Step S3: Based on the comparative analysis results, fault identification is performed on the field equipment to complete the status monitoring of the field equipment in the control system.

[0099] Specifically, if Z(t) is always equal to the actual observed value X(t), that is, the expected behavior output Y(t) is always zero or a fixed value, or Z(t) jumps to a preset multiple exceeding the normal fluctuation range within a preset time, or Z(t) presents a completely random pattern and no longer has any correlation with the system input or other related variables, and persists until exceeding the preset time threshold, then it is determined that the field equipment is in a hard fault state of complete damage.

[0100] If the absolute value of Z(t) shows an upward trend in the past N time units, and the increase exceeds the preset threshold A, it is determined that the field equipment is in a soft fault state with deteriorated performance; if the standard deviation of Z(t) increases by more than the preset threshold B in the past M time units, it is determined that the field equipment is in a soft fault state with deteriorated performance; if the spectrum analysis of Z(t) shows that the energy increase within a specific frequency range exceeds the preset threshold C, it is determined that the field equipment is in a soft fault state with deteriorated performance.

[0101] In summary, the digital twin model constructed by the present invention not only takes into account the static characteristics of the equipment, but also includes historical operating environment data and dynamic response behavior data, so as to more accurately reflect the overall status of the equipment. Secondly, by obtaining the second relevant data of the equipment and comparing and analyzing it with the expected behavior of the digital twin model, real-time and dynamic status monitoring is achieved to adapt to the dynamic changes in equipment performance, thus overcoming the limitations of traditional fixed models. Finally, fault identification is performed based on the results of comparative analysis, which can not only diagnose existing faults, but also has the ability to predict potential faults, thus achieving preventive maintenance. The present invention integrates multi-source data to improve the comprehensiveness and accuracy of monitoring; through digital twin technology, dynamic monitoring combining virtual and real is achieved, and the real-time and adaptability of the system are enhanced; at the same time, through comparative analysis and intelligent identification, the fault prediction and prevention capabilities are improved, greatly improving the effect and efficiency of equipment status monitoring.

[0102] Example 2

[0103] On the basis of the first embodiment, this embodiment further provides a state monitoring system for field equipment in a control system, which is composed of a model building module, a collection and analysis module, and an identification and monitoring module.

[0104] Among them, the model building module is used to build a digital twin model about the field device based on the first relevant data of the field device.

[0105] The acquisition and analysis module is used to obtain second relevant data of the field equipment, and compare and analyze the second relevant data with the expected behavior of the digital twin model.

[0106] The identification and monitoring module is used to identify faults of the field equipment based on the comparative analysis results, and complete the status monitoring of the field equipment in the control system.

[0107] This embodiment also provides a computer device, which is suitable for the state monitoring method of field equipment in a control system, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the state monitoring method of field equipment in a control system as proposed in the above embodiment.

[0108] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0109] This embodiment further provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for state monitoring of a field device in a control system as proposed in the above embodiment is implemented.

[0110] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0111] Example 3

[0112] This is the third embodiment of the present invention. Based on the previous two embodiments, this embodiment provides a state monitoring method for field equipment in a control system. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0113] The key equipment in the turbine control system of a 600MW supercritical thermal power unit was selected as the test object, including the main steam valve fast closing solenoid valve (FSV), the regulating valve position sensor and the bearing vibration sensor. The experiment lasted for 180 days, and the sampling frequency was determined according to the characteristics of different equipment. The FSV state was sampled once per second, the valve position was sampled once every 100ms, and the bearing vibration was sampled once every 10ms. The method of the present invention was compared with two existing methods: an alarm system based on a fixed threshold and a fault diagnosis system based on a fuzzy neural network.

[0114] As shown in Table 1, the present invention is significantly superior to existing methods in terms of detection accuracy, false alarm rate, and missed alarm rate. In particular, in terms of average detection time, the present invention can detect potential faults in just 8.7 minutes, which is nearly 4 times faster than the fixed threshold alarm system. This significant improvement is due to the fact that the digital twin model used in the present invention can simulate the dynamic characteristics of the equipment in real time and make accurate predictions based on historical data.

[0115] Table 1: Comparison of fault detection performance of different methods

[0116] method Detection accuracy False Positive Rate False negative rate Average detection time (minutes) The present invention 98.3％ 1.2％ 1.5％ 8.7 Fixed threshold alarm system 87.6％ 7.8％ 9.4％ 35.2 Fuzzy Neural Network System 93.5％ 3.9％ 4.7％ 19.6

[0117] As shown in Table 2, in terms of soft fault monitoring of performance degradation, the present invention can detect 95.7% of performance degradation, which is much higher than the other two methods. More importantly, through the dynamic behavior model of the present invention, the present invention can issue a performance degradation warning 12.5 days in advance, providing maintenance personnel with sufficient reaction time and capturing slight changes in equipment performance. For example, for a control valve, the present invention can predict possible performance degradation in advance by analyzing the changing trends of multiple parameters such as valve position, valve response time, and valve friction.

[0118] Table 2: Detection capabilities of different methods for device performance degradation

[0119] method Performance degradation detection rate False positive rate Advance warning time (days) The present invention 95.7％ 2.8％ 12.5 Fixed threshold alarm system 68.3％ 13.6％ 3.2 Fuzzy Neural Network System 82.1％ 7.4％ 7.8

[0120] In summary, the present invention is significantly superior to the existing technical solutions in multiple key indicators. It not only improves the accuracy and timeliness of fault detection, but also greatly enhances the ability to identify and predict equipment performance degradation. Although the demand for computing resources has increased, considering the operational safety and economic benefits of thermal power units, this investment is very worthwhile. This method provides a more advanced and effective solution for equipment status monitoring and predictive maintenance in thermal power plants.

[0121] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for monitoring the status of field equipment in a control system, characterized in that: include, Building a digital twin model of the field device based on first relevant data of the field device; the first relevant data includes static data, historical operating environment data and historical dynamic response behavior data of the field device; the digital twin model includes a three-dimensional model, an operating environment model and a dynamic behavior model; Acquire second relevant data of the field device, and compare and analyze the second relevant data with expected behavior of the digital twin model; Based on the comparative analysis results, fault identification is performed on the field equipment to complete the status monitoring of the field equipment in the control system.

2. The method for monitoring the state of a field device in a control system according to claim 1, characterized in that: The field devices include sensors and actuators; The construction process of the digital twin model includes the following steps: Establishing a three-dimensional model of the field equipment according to static data of the field equipment; the static data includes geometric data, material data and structural data; Establishing an operating environment model of the field device according to historical operating environment data; the historical operating environment data includes ambient temperature, ambient humidity and ambient pressure; Establishing a dynamic behavior model of the field device according to historical dynamic response behavior data; Integrating the three-dimensional model, the operating environment model and the dynamic behavior model of the field device into a digital twin model of the field device; The field device and the operating environment of the field device are mapped to the virtual space in real time through the digital twin model of the field device.

3. The method for monitoring the state of a field device in a control system according to claim 2, characterized in that: Establishing a three-dimensional model of the field device according to the static data of the field device comprises the following steps: constructing a three-dimensional geometric domain V based on the three-dimensional geometric shape of the field device; Discretize the three-dimensional geometric domain V into a plurality of units; combine the shape function matrix N, the material stiffness matrix D determined by the material data, and the shape function derivative matrix B determined by the structural data to obtain the response of each unit; Perform multiple integration accumulation on the response of each unit in the three-dimensional geometric domain V to obtain the total response of the three-dimensional geometric domain V, that is, the three-dimensional model M1; Establishing the operating environment model of the field device according to the historical operating environment data comprises the following steps: constructing an environmental temperature model according to the historical environmental temperature data, and performing nonlinear mapping on the historical environmental temperature data through the environmental temperature model; Constructing an environmental humidity model according to historical environmental humidity data, and performing nonlinear mapping on the historical environmental humidity data through the environmental humidity model; Constructing an environmental pressure model according to the historical environmental pressure data, and performing nonlinear mapping on the historical environmental pressure data through the environmental pressure model; According to the environmental temperature model, the environmental humidity model and the environmental pressure model, a comprehensive nonlinear mapping model is obtained; A comprehensive weight factor is introduced, and combined with the comprehensive nonlinear mapping model, to construct the operating environment model of the field equipment; wherein the comprehensive weight factor refers to the comprehensive weight of combining historical ambient temperature data, historical ambient humidity data and historical ambient pressure data, and the comprehensive influence of different environmental parameters on the operating status of the equipment is obtained through the comprehensive weight factor.

4. The method for monitoring the state of a field device in a control system according to claim 3, characterized in that: The historical dynamic response behavior data includes historical time response, historical measurement accuracy, historical vibration data, historical accumulated operating time, and historical current consumption of the field device; Establishing a dynamic behavior model of the field device according to historical dynamic response behavior data includes the following steps: determining a performance indicator for monitoring dynamic behavior of a field device based on historical time response, historical measurement accuracy, and historical vibration data of the field device; determining a degradation factor of the field device based on the historical accumulated operating time and the historical current consumption of the field device; The performance index and the degradation factor are combined to obtain a dynamic behavior model of the field device.

5. The method for monitoring the state of a field device in a control system according to claim 4, characterized in that: The formula of the digital twin model of the field equipment is: Among them, M(t) is the digital twin model output of the field equipment at time t; Ω is the parameterized geometric domain; J(x, t) is the Jacobi transformation factor; M1 is the three-dimensional model of the field equipment; M2(t) is the operating environment model; M3 is the dynamic behavior model; It is a comprehensive coupling function of three-dimensional model, dynamic behavior model and operating environment model.

6. The method for monitoring the state of a field device in a control system according to claim 5, characterized in that: The second related data refers to the operating environment data and dynamic response behavior data collected in real time; Comparing and analyzing the second relevant data with the expected behavior of the digital twin model includes the following steps: Acquire the second relevant data I(t) in real time; In combination with the second related data and the static data, the digital twin model M(t) is used to calculate the expected behavior output Y(t) of the field device: Among them, M2(I E (t)) is based on real-time operating environment data I E (t) operating environment model; M3(I D (t)) is based on real-time dynamic response behavior data I D (t) dynamic behavior model; Get the actual observation data X(t); The difference Z(t) between the expected behavior output Y(t) and the actual observed data X(t) is calculated, that is, the comparative analysis result.

7. The method for monitoring the state of a field device in a control system according to claim 6, characterized in that: Based on the comparative analysis results, fault identification is performed on the field device, including: If Z(t) is always equal to the actual observed value X(t), that is, the expected behavior output Y(t) is always zero or a fixed value, or Z(t) jumps to a preset multiple exceeding the normal fluctuation range within a preset time, or Z(t) presents a completely random pattern and no longer has any correlation with the system input or other related variables, and persists for more than a preset time threshold, then it is determined that the field device is in a hard fault state of complete damage; If the absolute value of Z(t) shows an upward trend in the past N time units, and the increase exceeds a preset threshold value A, it is determined that the field device is in a soft fault state with deteriorated performance; If the standard deviation of Z(t) increases by more than a preset threshold value B in the past M time units, it is determined that the field device is in a soft fault state with deteriorated performance; If the spectrum analysis of Z(t) shows that the energy increase in a specific frequency range exceeds a preset threshold value C, it is determined that the field device is in a soft fault state with degraded performance.

8. A state monitoring system for field equipment in a control system, based on the state monitoring method for field equipment in a control system according to any one of claims 1 to 7, characterized in that: include, A model building module, configured to build a digital twin model of the field device based on first relevant data of the field device; an acquisition and analysis module, configured to acquire second relevant data of the field device, and compare and analyze the second relevant data with the expected behavior of the digital twin model; The identification and monitoring module is used to identify faults of the field equipment based on the comparative analysis results, and complete the status monitoring of the field equipment in the control system.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for monitoring the state of a field device in a control system according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for monitoring the state of a field device in a control system according to any one of claims 1 to 7 are implemented.

Images