A data-driven based valve actuator state assessment method and system

Abstract

This invention relates to the field of equipment condition assessment technology, and provides a data-driven method and system for assessing the condition of valve actuators. The method includes: analyzing data from the target equipment to obtain a first type of time-series data sequence and a second type of time-series data sequence; dividing the first type of time-series data sequence into stages to obtain a segmented time-series dataset; performing a first feature analysis to obtain startup feature data; performing a second feature analysis to obtain operating feature data; performing a third feature analysis to obtain braking feature data; summarizing the startup feature data, operating feature data, and braking feature data to obtain a condition feature dataset; performing condition analysis based on the condition feature dataset to obtain a condition type set; obtaining associated feature parameters; performing condition analysis based on the condition type set and associated feature parameters to obtain a condition score set; and obtaining a condition assessment report. This invention solves the problem of low monitoring accuracy in the current process of assessing the condition of valve actuators.

Description

Technical Field

[0001] This invention relates to the field of equipment condition assessment technology, and in particular to a data-driven valve actuator condition assessment method and system. Background Technology

[0002] With the rapid development of industrial automation and process industries, valve actuators, as important equipment for fluid media control in process industries, energy and power, petrochemical, water supply and heating, etc., have their operational reliability directly related to the safety, stability and energy efficiency of the production system. Therefore, the condition assessment of valve actuators is of great significance.

[0003] Traditional valve actuator condition assessment methods rely heavily on manual inspections. While these methods can perform basic condition assessments, they lack the ability to monitor the valve actuator's operation process. Consequently, they cannot accurately identify abnormal conditions of internal components through monitoring data. Therefore, current valve actuator condition assessment methods suffer from low monitoring accuracy. Summary of the Invention

[0004] This invention provides a data-driven valve actuator status assessment method and system, the main purpose of which is to solve the problem of low monitoring accuracy in the current process of valve actuator status assessment.

[0005] To achieve the above objectives, the present invention provides a data-driven valve actuator status assessment method, comprising: Identify the target equipment; Data analysis is performed on the target device to obtain a first type of time-series data sequence and a second type of time-series data sequence; Based on the second type of time series data sequence, the first type of time series data sequence is divided into stages to obtain a segmented time series dataset, wherein the segmented time series dataset includes: a first stage time series data sequence, a second stage time series data sequence, and a third stage time series data sequence. Perform a first feature analysis on the first-stage time-series data sequence in the segmented time-series dataset to obtain startup feature data; The second feature analysis is performed on the time series data sequence of the second stage to obtain the running feature data; The third-stage time-series data sequence is subjected to a third feature analysis to obtain braking feature data; By summing the startup feature data, running feature data, and braking feature data, a state feature dataset is obtained. Based on the state feature dataset, state analysis is performed to obtain a set of state types; Obtain the associated feature parameters; Based on the state type set and associated feature parameters, state analysis is performed to obtain a state score set; Based on the set of state types and the set of state scores, obtain a state assessment report.

[0006] Optionally, the step of performing data analysis on the target device to obtain a first type of time-series data sequence and a second type of time-series data sequence includes: Based on the preset sampling frequency, synchronous data is collected from the target device to obtain the second type of time-series data sequence, the second time-series data sequence, the third time-series data sequence, and the fourth time-series data sequence; A first type of time series data sequence is constructed based on the second, third, and fourth time series data sequences.

[0007] Optionally, the step of dividing the first type of time-series data sequence into stages based on the second type of time-series data sequence to obtain a segmented time-series dataset includes: Based on the second type of time series data sequence, a state change rate sequence is obtained, wherein the state change rate sequence contains multiple state change rates; The state change rate sequence is divided into stages to obtain a set of stage starting points, wherein the set of stage starting points includes: the starting point of the first stage, the starting point of the second stage, and the starting point of the third stage. Using the set of stage starting points, the first type of time series data sequence is segmented and truncated to obtain the first stage time series data sequence, the second stage time series data sequence, and the third stage time series data sequence. The time series data sequences from the first stage, the second stage, and the third stage are combined to obtain a segmented time series dataset.

[0008] Optionally, the step of dividing the state change rate sequence into stages to obtain a set of stage starting points includes: Based on a preset first state change rate, the starting point of the first stage is determined from the state change rate sequence, wherein the starting point of the first stage is the first state change rate that is greater than or equal to the first state change rate among multiple state change rates in the state change rate sequence. Based on the preset second state change rate, the starting point of the second stage is determined from the state change rate sequence; Based on the starting point of the second stage and the first state change rate, the starting point of the third stage is identified from the state change rate sequence. By summing the starting points of the first stage, the second stage, and the third stage, we obtain the set of stage starting points.

[0009] Optionally, the step of performing a first feature analysis on the first-stage time-series data sequence in the segmented time-series dataset to obtain start-up feature data includes: The first startup data, the second startup data, and the third startup data were identified from the first phase time-series data sequence; Time-domain feature analysis was performed on the first startup data, the second startup data, and the third startup data to obtain the first feature set, the second feature set, and the third feature set. Startup feature analysis is performed on the first feature set, the second feature set, and the third feature set to obtain startup feature data.

[0010] Optionally, the step of performing startup feature analysis on the first feature set, the second feature set, and the third feature set to obtain startup feature data includes: The first startup peak, the second startup peak, and the third startup peak are extracted from the first feature set, the second feature set, and the third feature set, respectively. Energy analysis is performed on the first feature set, the second feature set, and the third feature set to obtain the first initial energy value, the second initial energy value, and the third initial energy value. The startup characteristic data are obtained by summarizing the first startup peak value, the first initial energy value, the second startup peak value, the second initial energy value, the third startup peak value, and the third initial energy value.

[0011] Optionally, the step of performing state analysis based on the state feature dataset to obtain a set of state types includes: Feature classification and extraction are performed on the start-up feature data, running feature data and braking feature data in the state feature dataset to obtain a first feature vector, a second feature vector and a third feature vector; The first feature vector, the second feature vector, and the third feature vector are concatenated to obtain the system feature vector; Based on the pre-built system feature library, feature comparison calculations are performed on the system feature vectors to obtain a feature similarity set; Based on a preset similarity threshold and a system feature library, the feature similarity set is filtered and matched to obtain a state type set, wherein the state type set includes one or more state types.

[0012] Optionally, the step of performing state analysis based on the state type set and associated feature parameters to obtain a state score set includes: For each state type in the set of state types, the following operation is performed: Based on the state type, obtain the state parameter set from the state feature dataset; Deviation is calculated based on the state parameter set and the preset benchmark parameter set to obtain the state parameter deviation set; Based on the set of deviations from the state parameters, obtain the comprehensive deviation. Based on the overall deviation, a status score is obtained; The state scores are summarized to obtain a state score set.

[0013] Optionally, obtaining the state score based on the comprehensive deviation includes: Based on the state type, an association parameter set is identified from the association feature parameters, wherein the association parameter set contains one or more association parameters; The deviation between the associated parameter set and the preset standard operating condition parameter set is calculated to obtain the operating condition deviation set, wherein the operating condition deviation set contains one or more operating condition deviations, and the operating condition deviations correspond one-to-one with the associated parameters. Based on the comprehensive deviation and operating condition deviation set, the status score is calculated using the following formula:

[0014] in, Indicates the status score. This indicates the preset basic score for the status. This represents the preset state deviation influence coefficient. Indicates the overall deviation. This indicates the number of associated parameters in the associated parameter set. Indicates the first in the set of associated parameters The weight coefficients of the associated parameters, Indicates the first in the set of associated parameters Deviation of operating conditions for each associated parameter This represents the preset operating condition influence coefficient. This represents the hyperbolic tangent function.

[0015] To achieve the above objectives, the present invention also provides a data-driven valve actuator status assessment system, comprising: The equipment data analysis module is used to identify the target equipment, perform data analysis on the target equipment, and obtain a first type of time-series data sequence and a second type of time-series data sequence. The data partitioning module is used to divide the first type of time series data sequence into stages based on the second type of time series data sequence to obtain a segmented time series dataset, wherein the segmented time series dataset includes: a first stage time series data sequence, a second stage time series data sequence, and a third stage time series data sequence. The data feature analysis module is used to perform a first feature analysis on the first stage time series data sequence in the segmented time series dataset to obtain startup feature data, perform a second feature analysis on the second stage time series data sequence to obtain running feature data, perform a third feature analysis on the third stage time series data sequence to obtain braking feature data, and summarize the startup feature data, running feature data and braking feature data to obtain a state feature dataset. The equipment status assessment module is used to perform status analysis based on the status feature dataset to obtain a status type set, acquire associated feature parameters, perform status analysis based on the status type set and associated feature parameters to obtain a status score set, and acquire a status assessment report based on the status type set and status score set.

[0016] To address the above problems, the present invention also provides an electronic device, the electronic device comprising: A memory that stores at least one instruction; and a processor that executes the instructions stored in the memory to implement the data-driven valve actuator status assessment method described above.

[0017] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the data-driven valve actuator status assessment method described above.

[0018] To address the problems described in the background art, this invention identifies the target device, clarifying the structural composition of the valve actuator and providing a hardware foundation for subsequent data acquisition and feature analysis. Data analysis is performed on the target device to obtain a first type of time-series data sequence and a second type of time-series data sequence. Based on the second type of time-series data sequence, the first type of time-series data sequence is divided into stages to obtain a segmented time-series dataset. This segmented time-series dataset includes a first-stage time-series data sequence, a second-stage time-series data sequence, and a third-stage time-series data sequence. A first feature analysis is performed on the first-stage time-series data sequence to obtain startup feature data. A second feature analysis is performed on the second-stage time-series data sequence to obtain operation feature data. A third feature analysis is performed on the third-stage time-series data sequence to obtain braking feature data. This invention analyzes the rate of change of state to classify the first type of time-series data sequence... The process is divided into three stages: startup, steady-state operation, and braking. Peak values ​​and energy characteristics are extracted for each stage to capture the vibration characteristics of various components under different motion states, improving the sensitivity for detecting abnormal conditions. The startup, operation, and braking characteristic data are summarized to obtain a state feature dataset. State analysis is performed based on this dataset to obtain a state type set. This invention identifies the type of abnormal condition by matching the system feature vector with a system feature library, improving the accuracy of state type identification. Corresponding feature parameters are obtained, and state analysis is performed based on the state type set and these parameters to obtain a state score set. A state assessment report is then generated based on the state type set and score set. This invention can collect and process physical signal data during valve actuator operation to extract characteristic data representing the equipment state, thereby achieving accurate diagnosis of the valve actuator's state. Therefore, this invention solves the problem of low monitoring accuracy in the current state assessment of valve actuators. Attached Figure Description

[0019] Figure 1 A flowchart illustrating a data-driven valve actuator status assessment method according to an embodiment of the present invention; Figure 2 A functional block diagram of a data-driven valve actuator status assessment system provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device for implementing the data-driven valve actuator status assessment method according to an embodiment of the present invention.

[0020] Explanation of reference numerals in the attached figures: 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0021] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0023] This application provides a data-driven valve actuator status assessment method. The execution entity of the data-driven valve actuator status assessment method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application embodiment: a server, a terminal, etc. In other words, the data-driven valve actuator status assessment method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0024] Reference Figure 1 The diagram shown is a flowchart illustrating a data-driven valve actuator status assessment method according to an embodiment of the present invention. In this embodiment, the data-driven valve actuator status assessment method includes: S1. Determine the target device, perform data analysis on the target device, and obtain a first type of time-series data sequence and a second type of time-series data sequence.

[0025] It should be explained that the target device refers to the device that needs to be assessed for its condition. Optionally, in this embodiment, the target device is a valve actuator and an associated valve. The associated valve refers to a valve that is directly mechanically connected to the valve actuator and is driven by the actuator to change its opening degree, such as a gate valve or a globe valve. The valve actuator refers to an execution system that controls the opening and closing of valves in industrial processes. Its main structure includes a drive motor, a gearbox, and a transmission mechanism. The drive motor refers to an electric motor that provides power to the valve actuator, such as a three-phase asynchronous motor. The gearbox refers to a speed-changing transmission component located between the drive motor and the transmission mechanism. It can adjust the speed and torque of the drive motor through internal gears to make the output power more stable. The transmission mechanism refers to a mechanical component that connects the gearbox and the associated valve. Its function is to transmit the mechanical power output from the gearbox to the associated valve to realize the opening degree adjustment of the associated valve.

[0026] In detail, the data analysis of the target device to obtain a first type of time-series data sequence and a second type of time-series data sequence includes: Based on the preset sampling frequency, synchronous data is collected from the target device to obtain the second type of time-series data sequence, the second time-series data sequence, the third time-series data sequence, and the fourth time-series data sequence; A first type of time series data sequence is constructed based on the second, third, and fourth time series data sequences.

[0027] Furthermore, the synchronous data acquisition of the target device to obtain a second type of time-series data sequence, a second time-series data sequence, a third time-series data sequence, and a fourth time-series data sequence includes: Acquire vibration signal acquisition unit and position signal acquisition unit; Based on the vibration signal acquisition unit, the acquisition units are arranged for the drive motor, gearbox and transmission mechanism in the valve actuator to obtain motor acquisition nodes, gearbox acquisition nodes and transmission mechanism acquisition nodes. Based on the position signal acquisition unit, the associated valves are arranged in units to obtain valve position acquisition nodes; Based on the sampling frequency, synchronous data is collected from the valve position acquisition node, motor acquisition node, gearbox acquisition node, and transmission mechanism acquisition node to obtain the second type of time-series data sequence, the second time-series data sequence, the third time-series data sequence, and the fourth time-series data sequence.

[0028] It should be noted that the vibration information acquisition unit refers to a device used to collect mechanical vibration signals from various components (drive motor, gearbox, transmission mechanism) of the valve actuator, such as a vibration tester. The position information acquisition unit refers to a device used to detect the opening degree of the associated valve, such as a magnetostrictive displacement sensor or a rotary encoder. The acquisition unit arrangement refers to the process of placing vibration information acquisition units at the locations of the drive motor, gearbox, and transmission mechanism of the valve actuator. The motor acquisition node refers to the point where a vibration signal acquisition unit is installed at the drive motor. The gearbox acquisition node refers to the point where a vibration signal acquisition unit is installed at the gearbox. The transmission mechanism acquisition node refers to the point where a vibration signal acquisition unit is installed at the transmission mechanism. The unit arrangement refers to the process of placing position information acquisition units on the associated valve to ensure that the position information acquisition units can detect changes in the opening degree of the associated valve. The valve position acquisition node refers to the point where a position signal acquisition unit is installed at the associated valve. The sampling frequency refers to the number of times data is collected per unit time as preset by the user; optionally, it can be set to 1000Hz.

[0029] It is understood that the synchronous data acquisition refers to the process where the valve position acquisition node, motor acquisition node, gearbox acquisition node, and transmission mechanism acquisition node, based on a unified time reference (such as GPS timing or IoT gateway synchronization clock), begin data acquisition at the same time point after the valve actuator starts. The second type of time-series data sequence refers to the sequence formed by arranging the valve opening data acquired by the valve position acquisition node in ascending order of time. The second time-series data sequence refers to the sequence formed by arranging the vibration signals acquired by the motor acquisition node in ascending order of time. The third time-series data sequence refers to the sequence formed by arranging the vibration signals acquired by the gearbox acquisition node in ascending order of time. The fourth time-series data sequence refers to the sequence formed by arranging the vibration signals acquired by the transmission mechanism acquisition node in ascending order of time. Constructing the first type of time-series data sequence based on the second, third, and fourth time-series data sequences means integrating the second, third, and fourth time-series data sequences into a single set, which is the first type of time-series data sequence. In this case, each element in the first type of time series data sequence is the corresponding data in the second, third, and fourth time series data sequences collected at the same time. For example, if the second time series data sequence is {a1, a2, a3}, the third time series data sequence is {b1, b2, b3}, and the fourth time series data sequence is {c1, c2, c3}, then the first type of time series data sequence is {(a1, b1, c1), (a2, b2, c2), (a3, b3, c3)}.

[0030] S2. Based on the second type of time series data sequence, the first type of time series data sequence is divided into stages to obtain a segmented time series dataset, wherein the segmented time series dataset includes: a first stage time series data sequence, a second stage time series data sequence, and a third stage time series data sequence.

[0031] It should be explained that the phase division refers to dividing the second type of time series data sequence into three phases: the startup phase, the steady-state operation phase, and the braking phase. The portion of the first type of time series data sequence corresponding to the duration of the startup phase constitutes the first phase time series data sequence; the portion corresponding to the duration of the steady-state operation phase constitutes the second phase time series data sequence; and the portion corresponding to the duration of the braking phase constitutes the third phase time series data sequence. The startup phase, steady-state operation phase, and braking phase will be explained in subsequent embodiment steps.

[0032] Specifically, based on the second type of time-series data sequence, the first type of time-series data sequence is divided into stages to obtain a segmented time-series dataset, including: Based on the second type of time series data sequence, a state change rate sequence is obtained, wherein the state change rate sequence contains multiple state change rates; The state change rate sequence is divided into stages to obtain a set of stage starting points, wherein the set of stage starting points includes: the starting point of the first stage, the starting point of the second stage, and the starting point of the third stage. Using the set of stage starting points, the first type of time series data sequence is segmented and truncated to obtain the first stage time series data sequence, the second stage time series data sequence, and the third stage time series data sequence. The time series data sequences from the first stage, the second stage, and the third stage are combined to obtain a segmented time series dataset.

[0033] Specifically, the process of dividing the state change rate sequence into stages to obtain a set of stage starting points includes: Based on a preset first state change rate, the starting point of the first stage is determined from the state change rate sequence, wherein the starting point of the first stage is the first state change rate that is greater than or equal to the first state change rate among multiple state change rates in the state change rate sequence. Based on the preset second state change rate, the starting point of the second stage is determined from the state change rate sequence; Based on the starting point of the second stage and the first state change rate, the starting point of the third stage is identified from the state change rate sequence. By summing the starting points of the first stage, the second stage, and the third stage, we obtain the set of stage starting points.

[0034] It should be understood that obtaining the state change rate sequence based on the second type of time-series data sequence means: performing a first-order difference calculation on the second type of time-series data sequence to obtain a sequence composed of state change rates (in this example, the state change rate is the change in valve opening per unit time, for example: 1% / s) in chronological order. The resulting sequence is the state change rate sequence. The method of performing the first-order difference calculation on the second type of time-series data sequence is existing technology and will not be described in detail here. The first state change rate refers to a pre-set critical value of the state change rate. When a state change rate greater than or equal to the first state change rate appears for the first time in the state change rate sequence, it indicates that the associated valve has entered the start-up stage. Optionally, the first state change rate can be set to 1% / s. The second state change rate refers to a pre-set critical value of the state change rate. When a state change rate less than or equal to the second state change rate appears for the first time after the start point of the first stage in the state change rate sequence, it indicates that the associated valve has entered the steady-state operation stage. Optionally, the second state change rate can be set to 0.1% / s. The starting point of the second stage refers to the first state change rate that is less than or equal to the second state change rate among multiple position change rates in the state change rate sequence after the starting point of the first stage.

[0035] It should be explained that, in the context of identifying the third stage starting point from the state change rate sequence based on the second stage starting point and the first state change rate, the first state change rate in the state change rate sequence that is less than or equal to the opposite value of the first state change rate is the third stage starting point. The segmentation refers to dividing the vibration time sequence signal into three corresponding intervals (i.e., the startup phase, steady-state operation phase, and braking phase) based on the times corresponding to the first, second, and third stage starting points. The startup phase refers to the time interval defined in the vibration time sequence signal between the times corresponding to the first and second stage starting points. The steady-state operation phase refers to the time interval defined in the vibration time sequence signal between the times corresponding to the second and third stage starting points. The braking phase refers to the time interval defined in the vibration time sequence signal between the times corresponding to the third stage starting point and the time when synchronous data acquisition is completed. The segmented time series dataset refers to the set formed by summarizing the time series data sequences of the first stage, the second stage, and the third stage.

[0036] S3. Perform a first feature analysis on the first stage time series data sequence in the segmented time series dataset to obtain the startup feature data.

[0037] Specifically, the first feature analysis is performed on the first-stage time-series data sequence in the segmented time-series dataset to obtain start-up feature data, including: The first startup data, the second startup data, and the third startup data were identified from the first phase time-series data sequence; Time-domain feature analysis was performed on the first startup data, the second startup data, and the third startup data to obtain the first feature set, the second feature set, and the third feature set. Startup feature analysis is performed on the first feature set, the second feature set, and the third feature set to obtain startup feature data.

[0038] Specifically, the step of performing startup feature analysis on the first feature set, the second feature set, and the third feature set to obtain startup feature data includes: The first startup peak, the second startup peak, and the third startup peak are extracted from the first feature set, the second feature set, and the third feature set, respectively. Energy analysis is performed on the first feature set, the second feature set, and the third feature set to obtain the first initial energy value, the second initial energy value, and the third initial energy value. The startup characteristic data are obtained by summarizing the first startup peak value, the first initial energy value, the second startup peak value, the second initial energy value, the third startup peak value, and the third initial energy value.

[0039] It should be noted that the first startup data refers to the set of vibration signals at the drive motor collected by the drive motor acquisition node in the first stage of the time-series data sequence. The second startup data refers to the set of vibration signals at the gearbox collected by the gearbox acquisition node in the first stage of the time-series data sequence. The third startup data refers to the set of vibration signals at the transmission mechanism collected by the transmission mechanism acquisition node in the first stage of the time-series data sequence. The time-domain impact analysis refers to the process of identifying the impact characteristics of the first, second, and third start-up data, respectively. The specific identification steps are as follows: An impact threshold is set (based on the first, second, and third start-up data; for example, if the identified information is the first start-up data, the impact threshold is set to three times the standard deviation of the vibration amplitude of all vibration signals in the first start-up data; for example, if the standard deviation of the first start-up data is k1, then the impact threshold is set to 3k1). All vibration signals in the vibration information (i.e., one of the first, second, and third start-up data) that are greater than or equal to the impact threshold are identified as candidate impact points. Candidate impact points whose time interval (i.e., the absolute value of the difference between the data acquisition times of two candidate impact points) is less than a preset time interval threshold (e.g., 0.01 seconds) are integrated into one impact point. (When the time interval is less than the time interval threshold, it indicates that the two candidate impact points are relatively close in time and belong to the same continuous vibration response generated by the same event, requiring integration, i.e., classification into the same event, to prevent multiple duplicate records. If the time interval is not less than the time interval threshold, it indicates that the two candidate impact points are relatively distant in time and should be considered as two independent events.) The first feature set refers to the set of all impact points obtained after performing time-domain impact analysis on the first startup data. The second feature set refers to the set of all impact points obtained after performing time-domain impact analysis on the second startup data. The third feature set refers to the set of all impact points obtained after performing time-domain impact analysis on the third startup data.

[0040] It is understood that the first initiation peak value refers to the maximum vibration amplitude among all impact points in the first feature set. The second initiation peak value refers to the maximum vibration amplitude among all impact points in the second feature set. The third initiation peak value refers to the maximum vibration amplitude among all impact points in the third feature set. The energy analysis refers to the process of calculating the energy for the first, second, and third feature sets respectively, specifically: calculating the energy of each impact point in each of the three impact sets using the following formula: in, Indicates the impact concentration of the first The energy at each impact point This indicates the duration of the impact point (i.e., the end time of the impact point minus the start time). Indicates the first The number of candidate impact points within each impact point Indicates the first Within the first impact point The vibration amplitude at each impact point. The first initial energy value refers to the total energy obtained by summing the energies of all impact points in the first feature set. The second initial energy value refers to the total energy obtained by summing the energies of all impact points in the second feature set. The third initial energy value refers to the total energy obtained by summing the energies of all impact points in the third feature set. The initial energy reflects the cumulative damage of the impact on the three components (i.e., the first initial energy value corresponds to the drive motor, the second initial energy value corresponds to the gearbox, and the third initial energy value corresponds to the transmission mechanism). The larger the initial energy, the more severe the cumulative damage to the components. The starting characteristic data refers to the set formed by summing the first starting peak value, the first initial energy value, the second starting peak value, the second initial energy value, the third starting peak value, and the third initial energy value.

[0041] S4. Perform a second feature analysis on the second stage time series data sequence to obtain operational feature data, and perform a third feature analysis on the third stage time series data sequence to obtain braking feature data.

[0042] It should be explained that the methods for the second and third feature analyses are consistent with those for the first feature analysis, and will not be repeated here. The operational feature data refers to the set of feature data for the three components in the steady-state operation phase obtained after performing the second feature analysis on the second-stage vibration sensing data sequence, including: motor steady-state operating peak value, motor steady-state operating energy, gearbox steady-state operating peak value, gearbox steady-state operating energy, transmission mechanism steady-state operating peak value, and transmission mechanism steady-state operating energy. The motor steady-state operating peak value refers to the first starting peak value of the drive motor in the steady-state operation phase. The motor steady-state operating energy refers to the first initial energy value of the drive motor in the steady-state operation phase. The gearbox steady-state operating peak value refers to the second starting peak value of the gearbox in the steady-state operation phase. The gearbox steady-state operating energy refers to the second initial energy value of the gearbox in the steady-state operation phase. The transmission mechanism steady-state operating peak value refers to the third starting peak value of the transmission mechanism in the steady-state operation phase. The transmission mechanism steady-state operating energy refers to the third initial energy value of the transmission mechanism in the steady-state operation phase. The methods for obtaining the steady-state peak value of the motor, the steady-state energy of the motor, the steady-state peak value of the gearbox, the steady-state energy of the gearbox, the steady-state peak value of the transmission mechanism, and the steady-state energy of the transmission mechanism are the same as those for obtaining the first starting peak value, the first initial energy value, the second starting peak value, the second initial energy value, the third starting peak value, and the third initial energy value, and will not be repeated here.

[0043] It should be noted that the braking characteristic data refers to the set of characteristic data of the three components during the braking stage, obtained after performing third characteristic analysis on the third-stage vibration sensing data sequence. This set includes: motor braking peak value, motor braking energy, gearbox braking peak value, gearbox braking energy, transmission mechanism braking peak value, and transmission mechanism braking energy. The motor braking peak value refers to the first starting peak value of the drive motor during the braking stage. The motor braking energy refers to the first initial energy value of the drive motor during the braking stage. The gearbox braking peak value refers to the second starting peak value of the gearbox during the braking stage. The gearbox braking energy refers to the second initial energy value of the gearbox during the braking stage. The transmission mechanism braking peak value refers to the third starting peak value of the transmission mechanism during the braking stage. The transmission mechanism braking energy refers to the third initial energy value of the transmission mechanism during the braking stage. The methods for obtaining the motor braking peak value, motor braking energy, gearbox braking peak value, gearbox braking energy, transmission mechanism braking peak value, and transmission mechanism braking energy are consistent with the methods for obtaining the first starting peak value, first initial energy value, second starting peak value, second initial energy value, third starting peak value, and third initial energy value, and will not be repeated here.

[0044] S5. Summarize the startup feature data, running feature data and braking feature data to obtain a state feature dataset. Perform state analysis based on the state feature dataset to obtain a state type set.

[0045] It should be noted that the state characteristic data refers to the set formed by summarizing the start-up characteristic data, running characteristic data, and braking characteristic data.

[0046] Furthermore, the step of performing state analysis based on the state feature dataset to obtain a set of state types includes: Feature classification and extraction are performed on the start-up feature data, running feature data and braking feature data in the state feature dataset to obtain a first feature vector, a second feature vector and a third feature vector; The first feature vector, the second feature vector, and the third feature vector are concatenated to obtain the system feature vector; Based on the pre-built system feature library, feature comparison calculations are performed on the system feature vectors to obtain a feature similarity set; Based on a preset similarity threshold and a system feature library, the feature similarity set is filtered and matched to obtain a state type set, wherein the state type set includes one or more state types.

[0047] It should be explained that the feature classification extraction refers to the process of extracting feature data from the startup feature data, operation feature data, and braking feature data belonging to the same component according to the component type, and then summarizing the feature data to construct a vector. For example, if the component is a drive motor, the corresponding feature data extracted from the startup feature data, operation feature data, and braking feature data of the drive motor would be {first startup peak value, first initial energy value, motor steady-state operation peak value, motor steady-state operation energy, motor braking peak value, motor braking energy}. The method of summarizing the feature data to construct a vector is existing technology and will not be described in detail here. The first feature vector refers to the vector composed of the feature data of the drive motor. The second feature vector refers to the vector composed of the feature data of the gearbox. The third feature vector refers to the vector composed of the feature data of the transmission mechanism. The vector concatenation refers to the process of joining the first, second, and third feature vectors in a preset order (e.g., motor → gearbox → transmission mechanism) to form a higher-dimensional vector. For example, if the first feature vector is {G1, G2, G3, G4, G5, G6}, the second feature vector is {Q1, Q2, Q3, Q4, Q5, Q6}, and the third feature vector is {X1, X2, X3, X4, X5, X6}, then the merged vector is {G1, G2, G3, G4, G5, G6, Q1, Q2, Q3, Q4, Q5, Q6, X1, X2, X3, X4, X5, X6}. The actuator feature vector refers to the higher-dimensional vector obtained by concatenating the first, second, and third feature vectors.

[0048] It is understood that the actuator feature library refers to a pre-constructed database, compiled by relevant personnel through statistical analysis of a large number of historical failure events. This database contains different state types and their corresponding actuator feature vectors. The feature comparison calculation refers to the process of calculating the similarity between each actuator feature vector and an actuator feature vector in the actuator feature library using a preset similarity calculation method. Optionally, cosine similarity can be used as the similarity calculation method. The feature similarity set refers to the collection of all feature similarities. The feature similarity refers to a quantitative index obtained through feature comparison calculation, representing the degree of similarity between an actuator feature vector and a certain actuator feature vector in the actuator feature library. The greater the feature similarity, the more similar the actuator feature vector is to a certain actuator feature vector in the feature library.

[0049] It should be explained that the similarity threshold refers to a pre-set critical value for feature similarity. When the feature similarity is greater than the similarity threshold, it can be determined that the actuator feature vector matches the corresponding actuator feature vector in the actuator feature library. The filtering and matching refers to the process of filtering out all actuator feature vectors in the actuator feature library whose feature similarity is greater than the similarity threshold from the feature similarity set, and summarizing the state types corresponding to all the filtered actuator feature vectors into a set. The state type set refers to the set formed by summarizing the filtered state types after filtering and matching. The state type refers to the possible fault categories of the valve actuator, which can be divided into: drive motor faults, gearbox faults, and transmission mechanism faults. The drive motor faults refer to faults of the drive motor itself or its associated components, involving mechanical and electrical abnormalities of the motor, such as: insufficient lubrication of the drive motor bearings (insufficient bearing lubrication causing wear), unbalanced drive motor rotors (uneven rotor mass distribution causing vibration), and excessive drive motor bearing clearance (excessive bearing clearance causing excessive impact), etc. The gearbox fault category refers to malfunctions of gears, bearings, or the gearbox housing itself, involving abnormal gear meshing and bearing operation. Specific examples include: gear wear (gear surface friction leading to dimensional changes), gear bearing jamming (bearing balls or raceways obstructing, causing increased resistance), and damaged bearing balls. The transmission mechanism fault category refers to transmission mechanism malfunctions, involving mechanical abnormalities in the power transmission process. Specific examples include: loose connecting rods (excessive clearance between the connecting rod and hinge point causing increased impact), worn nut in the transmission mechanism (worn nut threads causing transmission jamming), and corrosion at the hinge point in the transmission mechanism (increased friction at the hinge point leading to increased resistance). It should be noted that if no actuator feature vector in the actuator feature library has a similarity greater than the similarity threshold, it indicates that the valve actuator is not faulty. In this case, this result can be used as the result of this condition assessment to complete the condition assessment.

[0050] S6. Obtain the associated feature parameters, perform state analysis based on the state type set and associated feature parameters, and obtain the state score set.

[0051] Specifically, obtaining the associated feature parameters includes: Determine valve dispatch instructions; The target valve opening data is confirmed from the valve scheduling command; Based on the valve actuator, valve actuator status analysis is performed to obtain valve status data and valve load data; Based on the valve target opening data, valve status data, and valve load data, associated feature parameters are constructed.

[0052] The step of performing valve actuator state analysis based on the valve actuator to obtain valve state information and valve load information includes: The associated process pipelines are acquired, and the medium data of the associated process pipelines are monitored to obtain the medium pressure sequence and the medium temperature sequence. Steady-state features were extracted from the medium pressure sequence and the medium temperature sequence respectively to obtain the medium pressure value and the medium temperature value. By summarizing the medium pressure and temperature values, the valve status information can be obtained; Obtain the rated speed and rated voltage of the drive motor in the valve actuator; The drive circuit current of the drive motor is extracted to obtain the drive motor current; Calculate the load torque of the drive motor based on the drive motor current, rated speed, and rated voltage; By summarizing the drive motor current and drive motor load torque, the valve load information is obtained.

[0053] It should be understood that the valve scheduling instruction refers to the instruction issued by relevant personnel to the valve actuator, such as adjusting the valve opening from 30% to 70%. The valve target opening data refers to the opening degree that the associated valve needs to achieve. Based on the valve target opening data, the action target of the associated valve in the valve actuator status assessment can be determined (i.e., whether the associated valve needs to be opened or closed). Optionally, in this embodiment, the action target of the associated valve is opening. The construction of associated feature parameters based on the valve target opening data, valve status data, and valve load data means: summarizing the valve target opening data, valve status data, and valve load data into a set, which is the associated feature parameter.

[0054] It should be explained that the associated process pipeline refers to the process pipeline directly connected to the associated valve and used for transporting the process medium. Optionally, in this embodiment, water is used as the process medium. The medium data monitoring refers to the process of monitoring the pressure and temperature of the process medium in the process pipeline. The start time of monitoring is consistent with the start time of the valve actuator. Optionally, a pressure transmitter is used to monitor the pressure of the process medium, and a thermocouple sensor is used to monitor the temperature of the process medium. The medium pressure sequence refers to the sequence formed by arranging all the pressure data of the process medium obtained after medium data monitoring in chronological order from earliest to latest. The medium temperature sequence refers to the sequence formed by arranging all the temperature data of the process medium obtained after medium data monitoring in chronological order from earliest to latest. The step of performing steady-state characteristic analysis on the medium pressure sequence and the medium temperature sequence to obtain the medium pressure value and the medium temperature value respectively means: calculating the statistical characteristics of the medium pressure sequence and the medium temperature sequence respectively. The statistical characteristic of the medium pressure sequence is the medium pressure value, and the statistical characteristic of the medium temperature sequence is the medium temperature value. Optionally, the arithmetic mean is taken as the statistical characteristic.

[0055] It is understood that the valve status data refers to the set obtained by integrating the medium pressure and medium temperature values. The rated speed refers to the standard speed of the drive motor. The rated voltage refers to the standard operating voltage of the drive motor. Both the rated speed and rated voltage can be obtained by consulting the drive motor's nameplate. The drive circuit current extraction refers to the process of measuring the current in the drive motor's power supply circuit at a preset frequency (e.g., 1000Hz) using a current sensor (such as a Hall effect current sensor). Specifically, the current sensor is connected in series with the drive motor's power supply, and the operating current of the drive motor is continuously detected. The drive motor current refers to the arithmetic average of all currents measured by the current sensor. The drive motor load torque refers to the output torque of the drive motor during operation, and its calculation formula is: ,in, P represents the load torque of the drive motor, and P represents the output power of the motor. The rated speed is indicated by the motor output power, which refers to the power of the motor during operation. Its calculation formula is as follows: ,in, Indicates the rated voltage. Indicates the current of the drive motor. This represents the power factor of the drive motor. Indicates the motor efficiency of the drive motor; optional. and This information can be found in the manufacturer's manual for the drive motor. The valve load data refers to the set obtained by integrating the drive motor current and the drive motor load torque.

[0056] In detail, the state analysis based on the state type set and associated feature parameters to obtain a state score set includes: For each state type in the set of state types, the following operation is performed: Based on the state type, obtain the state parameter set from the state feature dataset; Deviation is calculated based on the state parameter set and the preset benchmark parameter set to obtain the state parameter deviation set; Based on the set of deviations from the state parameters, obtain the comprehensive deviation. Based on the overall deviation, a status score is obtained; The state scores are summarized to obtain a state score set.

[0057] Specifically, obtaining the status score based on the comprehensive deviation includes: Based on the state type, an association parameter set is identified from the association feature parameters, wherein the association parameter set contains one or more association parameters; The deviation between the associated parameter set and the preset standard operating condition parameter set is calculated to obtain the operating condition deviation set, wherein the operating condition deviation set contains one or more operating condition deviations, and the operating condition deviations correspond one-to-one with the associated parameters. Based on the comprehensive deviation and operating condition deviation set, the status score is calculated using the following formula:

[0058] in, Indicates the status score. This indicates the preset basic score for the status. This represents the preset state deviation influence coefficient. Indicates the overall deviation. This indicates the number of associated parameters in the associated parameter set. Indicates the first in the set of associated parameters The weight coefficients of the associated parameters, Indicates the first in the set of associated parameters Deviation of operating conditions for each associated parameter This represents the preset operating condition influence coefficient. This represents the hyperbolic tangent function.

[0059] It should be noted that obtaining the state parameter set from the state feature dataset according to the state type means: selecting state parameters related to the fault from the state feature dataset based on the component (drive motor, gearbox, transmission mechanism) to which the state type belongs. The set of selected state parameters constitutes the state parameter set. For example, if the state type is a drive motor fault, the state parameters extracted from the state feature dataset are the first starting peak value, the first initial energy value, the motor steady-state operating peak value, the motor steady-state operating energy, the motor braking impact peak value, and the motor braking energy. The reference parameter set refers to the set composed of all reference parameters. The reference parameter refers to the arithmetic mean of the parameters corresponding to a certain state parameter in the state parameter set when the valve actuator has not failed in the past historical records. The deviation calculation refers to the process of calculating the relative deviation (i.e., the state parameter deviation) between each state parameter in the state parameter set and its corresponding reference parameter in the reference parameter set. The formula for calculating the relative deviation is: ,in, This indicates taking the absolute value. The state parameter deviation set refers to the set of state parameter deviations corresponding one-to-one with each state parameter obtained after calculating the deviation for each state parameter in the state parameter set. The comprehensive deviation is a quantitative index representing the overall deviation between the state parameter set and the reference parameter set. The larger the comprehensive deviation, the greater the deviation between the state of the faulty component and its normal state, indicating that the performance degradation of the faulty component is more obvious, its potential damage is higher, and the component's condition is worse. The formula for calculating the comprehensive deviation is: ,in, Indicates the overall deviation. This indicates the number of state parameters in the state parameter set. Represents the first in the state parameter set The weighting coefficients of each state parameter. Represents the first in the state parameter set The deviation of each state parameter. Optionally, the weight coefficient of the state parameter is set according to the parameter type of the state parameter. For example, if the state parameter is a peak value (such as the first starting peak value, the steady-state operation peak value of the motor, etc.), the weight is 0.6; if the state parameter is an energy value (such as the first starting energy value, the steady-state operation energy of the motor, etc.), the weight is 0.4.

[0060] It is understood that the associated parameter set refers to a collection of valve characteristic parameters that directly affect the probability or severity of the occurrence of the state type. For example, if the state type is a drive motor failure, the associated parameters may include drive motor current and drive motor load torque; if the state type is a gearbox failure, the associated parameters may include medium temperature, drive motor load torque, and medium pressure; if the state type is a transmission mechanism failure, the associated parameters may include drive motor load torque and medium pressure. The standard operating condition parameter set refers to a collection of standard operating condition parameters. The standard operating condition parameters refer to the average value of the parameters corresponding to the associated parameters in the associated parameter set when the valve actuator is operating normally in historical records. The operating condition deviation refers to the relative deviation between the associated parameters in the associated parameter set and their corresponding standard operating condition parameters in the standard operating condition parameter set. The calculation method for the operating condition deviation is the same as that for the state parameter deviation, and will not be repeated here. The operating condition deviation set refers to a collection of all operating condition deviations.

[0061] It should be understood that the status score refers to a quantitative indicator representing the severity of a status problem; the higher the value, the more severe the corresponding status problem. The status baseline score refers to a pre-set baseline value based on the inherent risk of the status type. For example, a drive motor failure could be set to 1.5 (this type of failure may lead to power loss and has a high risk), a gearbox failure could be set to 2 (this type of failure often causes transmission chain failure or severe equipment damage and has the highest inherent risk), and a transmission mechanism failure could be set to 1 (because transmission mechanism failures usually manifest as a decrease in the accuracy of the opening or closing of associated valves, which has a relatively small impact on the safety of valve actuators). The status deviation influence parameter refers to a pre-set parameter representing the degree of influence of the overall deviation on the status score; optionally, the status deviation influence parameter can be set to 0.2. The operating condition influence coefficient refers to a pre-selected parameter representing the degree of influence of the operating condition deviation on the status score; optionally, the operating condition influence coefficient can be set to 0.1. The weighting coefficients of the correlation parameters are pre-set values. Optionally, the weighting coefficients of the correlation parameters can be set according to their correlation with the state type. For example, for drive motor type faults, the correlation parameters are drive motor current and drive motor load torque. The drive motor load torque has a high direct correlation with the fault, so the weighting coefficient of drive motor load torque can be set to 0.6, and the weighting coefficient of drive motor current can be set to 0.4. The state score set refers to the set composed of all state scores.

[0062] S7. Obtain a status assessment report based on the status type set and status score set.

[0063] It should be explained that the status score reflects the severity of the status problems of each component of the target equipment. Therefore, relevant personnel can determine the repair priority of the corresponding status problem based on the status type and the corresponding status score obtained from the status assessment, and then carry out subsequent problem repair.

[0064] To address the problems described in the background art, this invention identifies the target device, clarifying the structural composition of the valve actuator and providing a hardware foundation for subsequent data acquisition and feature analysis. Data analysis is performed on the target device to obtain a first type of time-series data sequence and a second type of time-series data sequence. Based on the second type of time-series data sequence, the first type of time-series data sequence is divided into stages to obtain a segmented time-series dataset. This segmented time-series dataset includes a first-stage time-series data sequence, a second-stage time-series data sequence, and a third-stage time-series data sequence. A first feature analysis is performed on the first-stage time-series data sequence to obtain startup feature data. A second feature analysis is performed on the second-stage time-series data sequence to obtain operation feature data. A third feature analysis is performed on the third-stage time-series data sequence to obtain braking feature data. This invention analyzes the rate of change of state to classify the first type of time-series data sequence... The process is divided into three stages: startup, steady-state operation, and braking. Peak values ​​and energy characteristics are extracted for each stage to capture the vibration characteristics of various components under different motion states, improving the sensitivity for detecting abnormal conditions. The startup, operation, and braking characteristic data are summarized to obtain a state feature dataset. State analysis is performed based on this dataset to obtain a state type set. This invention identifies the type of abnormal condition by matching the system feature vector with a system feature library, improving the accuracy of state type identification. Corresponding feature parameters are obtained, and state analysis is performed based on the state type set and these parameters to obtain a state score set. A state assessment report is then generated based on the state type set and score set. This invention can collect and process physical signal data during valve actuator operation to extract characteristic data representing the equipment state, thereby achieving accurate diagnosis of the valve actuator's state. Therefore, this invention solves the problem of low monitoring accuracy in the current state assessment of valve actuators.

[0065] like Figure 2 The diagram shown is a functional block diagram of a data-driven valve actuator status assessment system provided in an embodiment of the present invention.

[0066] The data-driven valve actuator status assessment system 100 described in this invention can be installed in an electronic device. Depending on the functions implemented, the data-driven valve actuator status assessment system 100 may include a device data analysis module 101, a data partitioning module 102, a data feature analysis module 103, and a device status assessment module 104. The module described in this invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device.

[0067] The device data analysis module 101 is used to determine the target device, perform data analysis on the target device, and obtain a first type of time series data sequence and a second type of time series data sequence. The data partitioning module 102 is used to divide the first type of time series data sequence into stages based on the second type of time series data sequence to obtain a segmented time series dataset, wherein the segmented time series dataset includes: a first stage time series data sequence, a second stage time series data sequence, and a third stage time series data sequence. The data feature analysis module 103 is used to perform a first feature analysis on the first stage time series data sequence in the segmented time series dataset to obtain startup feature data, perform a second feature analysis on the second stage time series data sequence to obtain running feature data, perform a third feature analysis on the third stage time series data sequence to obtain braking feature data, and summarize the startup feature data, running feature data and braking feature data to obtain a state feature dataset. The device status assessment module 104 is used to perform status analysis based on the status feature dataset to obtain a status type set, acquire associated feature parameters, perform status analysis based on the status type set and associated feature parameters to obtain a status score set, and acquire a status assessment report based on the status type set and status score set.

[0068] In detail, the modules in the data-driven valve actuator status assessment system 100 described in this embodiment of the invention employ the same methods as described above during use. Figure 1 The method used is the same as the data-driven valve actuator status assessment method described above, and it can produce the same technical effect, so it will not be repeated here.

[0069] like Figure 3 The diagram shown is a schematic representation of an electronic device for implementing a data-driven valve actuator status assessment method according to an embodiment of the present invention.

[0070] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a data-driven valve actuator status assessment method program.

[0071] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of a data-driven valve actuator status evaluation method program, but also to temporarily store data that has been output or will be output.

[0072] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a data-driven valve actuator status evaluation method program) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0073] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0074] Figure 3 Only electronic devices with components are shown; those skilled in the art will understand that... Figure 3The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0075] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management system, thereby enabling functions such as charging management, discharging management, and power consumption management through the power management system. The power supply may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0076] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0077] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0078] The data-driven valve actuator status evaluation method program stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When run in the processor 10, it can achieve the following: Identify the target equipment; Data analysis is performed on the target device to obtain a first type of time-series data sequence and a second type of time-series data sequence; Based on the second type of time series data sequence, the first type of time series data sequence is divided into stages to obtain a segmented time series dataset, wherein the segmented time series dataset includes: a first stage time series data sequence, a second stage time series data sequence, and a third stage time series data sequence. Perform a first feature analysis on the first-stage time-series data sequence in the segmented time-series dataset to obtain startup feature data; The second feature analysis is performed on the time series data sequence of the second stage to obtain the running feature data; The third-stage time-series data sequence is subjected to a third feature analysis to obtain braking feature data; By summing the startup feature data, running feature data, and braking feature data, a state feature dataset is obtained. Based on the state feature dataset, state analysis is performed to obtain a set of state types; Obtain the associated feature parameters; Based on the state type set and associated feature parameters, state analysis is performed to obtain a state score set; Based on the set of state types and the set of state scores, obtain a state assessment report.

[0079] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0080] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0081] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following: Identify the target equipment; Data analysis is performed on the target device to obtain a first type of time-series data sequence and a second type of time-series data sequence; Based on the second type of time series data sequence, the first type of time series data sequence is divided into stages to obtain a segmented time series dataset, wherein the segmented time series dataset includes: a first stage time series data sequence, a second stage time series data sequence, and a third stage time series data sequence. Perform a first feature analysis on the first-stage time-series data sequence in the segmented time-series dataset to obtain startup feature data; The second feature analysis is performed on the time series data sequence of the second stage to obtain the running feature data; The third-stage time-series data sequence is subjected to a third feature analysis to obtain braking feature data; By summing the startup feature data, running feature data, and braking feature data, a state feature dataset is obtained. Based on the state feature dataset, state analysis is performed to obtain a set of state types; Obtain the associated feature parameters; Based on the state type set and associated feature parameters, state analysis is performed to obtain a state score set; Based on the set of state types and the set of state scores, obtain a state assessment report.

[0082] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0083] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0084] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0085] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A data-driven method for assessing the condition of a valve actuator, characterized in that, The method includes: Identify the target equipment; Data analysis is performed on the target device to obtain a first type of time-series data sequence and a second type of time-series data sequence; Based on the second type of time series data sequence, the first type of time series data sequence is divided into stages to obtain a segmented time series dataset, wherein the segmented time series dataset includes: a first stage time series data sequence, a second stage time series data sequence, and a third stage time series data sequence. Perform a first feature analysis on the first-stage time-series data sequence in the segmented time-series dataset to obtain startup feature data; The second feature analysis is performed on the time series data sequence of the second stage to obtain the running feature data; The third-stage time-series data sequence is subjected to a third feature analysis to obtain braking feature data; By summarizing the startup feature data, operation feature data, and braking feature data, a state feature dataset is obtained. Based on the state feature dataset, state analysis is performed to obtain a set of state types; Obtain the associated feature parameters; Based on the state type set and associated feature parameters, state analysis is performed to obtain a state score set; Based on the set of state types and the set of state scores, obtain a state assessment report.

2. The data-driven valve actuator status assessment method as described in claim 1, characterized in that, The step of performing data analysis on the target device to obtain a first type of time-series data sequence and a second type of time-series data sequence includes: Based on the preset sampling frequency, synchronous data is collected from the target device to obtain the second type of time-series data sequence, the second time-series data sequence, the third time-series data sequence, and the fourth time-series data sequence; A first type of time series data sequence is constructed based on the second, third, and fourth time series data sequences.

3. The data-driven valve actuator status assessment method as described in claim 2, characterized in that, The first type of time-series data sequence is divided into stages based on the second type of time-series data sequence to obtain a segmented time-series dataset, including: Based on the second type of time series data sequence, a state change rate sequence is obtained, wherein the state change rate sequence contains multiple state change rates; The state change rate sequence is divided into stages to obtain a set of stage starting points, wherein the set of stage starting points includes: the starting point of the first stage, the starting point of the second stage, and the starting point of the third stage. Using the set of stage starting points, the first type of time series data sequence is segmented and truncated to obtain the first stage time series data sequence, the second stage time series data sequence, and the third stage time series data sequence. The time series data sequences from the first stage, the second stage, and the third stage are combined to obtain a segmented time series dataset.

4. The data-driven valve actuator status assessment method as described in claim 3, characterized in that, The process of dividing the state change rate sequence into stages to obtain a set of stage starting points includes: Based on a preset first state change rate, the starting point of the first stage is determined from the state change rate sequence, wherein the starting point of the first stage is the first state change rate that is greater than or equal to the first state change rate among multiple state change rates in the state change rate sequence. Based on the preset second state change rate, the starting point of the second stage is determined from the state change rate sequence; Based on the starting point of the second stage and the first state change rate, the starting point of the third stage is identified from the state change rate sequence. By summing the starting points of the first stage, the second stage, and the third stage, we obtain the set of stage starting points.

5. The data-driven valve actuator status assessment method as described in claim 4, characterized in that, The first feature analysis is performed on the first-stage time-series data sequence in the segmented time-series dataset to obtain start-up feature data, including: The first startup data, the second startup data, and the third startup data were identified from the first phase time-series data sequence; Time-domain feature analysis was performed on the first startup data, the second startup data, and the third startup data to obtain the first feature set, the second feature set, and the third feature set. Startup feature analysis is performed on the first feature set, the second feature set, and the third feature set to obtain startup feature data.

6. The data-driven valve actuator status assessment method as described in claim 5, characterized in that, The startup feature analysis of the first feature set, the second feature set, and the third feature set to obtain startup feature data includes: The first startup peak, the second startup peak, and the third startup peak are extracted from the first feature set, the second feature set, and the third feature set, respectively. Energy analysis is performed on the first feature set, the second feature set, and the third feature set to obtain the first initial energy value, the second initial energy value, and the third initial energy value. The startup characteristic data are obtained by summarizing the first startup peak value, the first initial energy value, the second startup peak value, the second initial energy value, the third startup peak value, and the third initial energy value.

7. The data-driven valve actuator status assessment method as described in claim 6, characterized in that, The step of performing state analysis based on the state feature dataset to obtain a set of state types includes: Feature classification and extraction are performed on the start-up feature data, running feature data and braking feature data in the state feature dataset to obtain a first feature vector, a second feature vector and a third feature vector; The first feature vector, the second feature vector, and the third feature vector are concatenated to obtain the system feature vector; Based on the pre-built system feature library, feature comparison calculations are performed on the system feature vectors to obtain a feature similarity set; Based on a preset similarity threshold and a system feature library, the feature similarity set is filtered and matched to obtain a state type set, wherein the state type set includes one or more state types.

8. The data-driven valve actuator status assessment method as described in claim 7, characterized in that, The state analysis based on the state type set and associated feature parameters yields a state score set, including: For each state type in the set of state types, the following operation is performed: Based on the state type, obtain the state parameter set from the state feature dataset; Deviation is calculated based on the state parameter set and the preset benchmark parameter set to obtain the state parameter deviation set; Based on the set of deviations from the state parameters, obtain the comprehensive deviation. Based on the overall deviation, a status score is obtained; The state scores are summarized to obtain a state score set.

9. The data-driven valve actuator status assessment method as described in claim 8, characterized in that, The process of obtaining a status score based on the comprehensive deviation includes: Based on the state type, an association parameter set is identified from the association feature parameters, wherein the association parameter set contains one or more association parameters; The deviation between the associated parameter set and the preset standard operating condition parameter set is calculated to obtain the operating condition deviation set, wherein the operating condition deviation set contains one or more operating condition deviations, and the operating condition deviations correspond one-to-one with the associated parameters. Based on the comprehensive deviation and operating condition deviation set, the status score is calculated using the following formula: ， in, Indicates the status score. This indicates the preset basic score for the status. This represents the preset state deviation influence coefficient. Indicates the overall deviation. This indicates the number of associated parameters in the associated parameter set. Indicates the first in the set of associated parameters The weight coefficients of the associated parameters, Indicates the first in the set of associated parameters Deviation of operating conditions for each associated parameter This represents the preset operating condition influence coefficient. This represents the hyperbolic tangent function.

10. A data-driven valve actuator condition assessment system, characterized in that, The system includes: The equipment data analysis module is used to identify the target equipment, perform data analysis on the target equipment, and obtain a first type of time-series data sequence and a second type of time-series data sequence. The data partitioning module is used to divide the first type of time series data sequence into stages based on the second type of time series data sequence to obtain a segmented time series dataset, wherein the segmented time series dataset includes: a first stage time series data sequence, a second stage time series data sequence, and a third stage time series data sequence. The data feature analysis module is used to perform a first feature analysis on the first stage time series data sequence in the segmented time series dataset to obtain startup feature data, perform a second feature analysis on the second stage time series data sequence to obtain running feature data, perform a third feature analysis on the third stage time series data sequence to obtain braking feature data, and summarize the startup feature data, running feature data and braking feature data to obtain a state feature dataset. The equipment status assessment module is used to perform status analysis based on the status feature dataset to obtain a status type set, acquire associated feature parameters, perform status analysis based on the status type set and associated feature parameters to obtain a status score set, and acquire a status assessment report based on the status type set and status score set.

Images