An intelligent test system and method for the whole life cycle of a valve actuator

Abstract

The present application provides a full life cycle intelligent testing system and method for valve actuators. The system includes: a composite load generation module, which is used to generate the initial dynamic ratio of axial thrust and radial disturbance force according to the test protocol instructions, simulate the comprehensive stress state of the actuator under the impact of the pipeline medium, and output mechanical data containing thrust fluctuation characteristics in real time; an environmental coupling module, which is used to dynamically adjust the environmental stress conditions according to the test protocol instructions; a digital twin analysis module, which is used to compare the actual displacement trajectory of the actuator with the theoretical model trajectory through a time-space alignment algorithm based on the mechanical data and the environmental stress conditions to obtain a deviation feature vector; an intelligent diagnosis module, which is used to perform dynamic time regularization matching based on the deviation feature vector and a preset historical fault database, output a fault type identification code and confidence, and generate a test report. The above scheme improves the accuracy of the precise assessment of the full life cycle status of the valve actuator.

Description

Technical Field

[0001] The present application relates to the field of valve testing equipment, and in particular to a full life cycle intelligent testing system and method for valve actuators. Background Art

[0002] In the field of industrial automation, the reliability of valve actuators is directly related to the safe operation of pipeline systems. Traditional testing systems usually use a method of superimposing static load tests with single environmental stresses, such as testing mechanical strength through constant axial thrust, or conducting salt spray corrosion tests at a fixed temperature. Although such methods can verify the performance of actuators under specific working conditions, it is difficult to simulate the dynamic working conditions in real pipelines. In particular, when the actuator causes minor faults due to factors such as material fatigue and seal aging during long-term operation, existing technologies generally use threshold alarms or waveform comparisons at a single time node, which cannot effectively capture the time-varying fault characteristics under the synergistic effect of dynamic loads and environmental stresses. This mismatch between static criteria and dynamic working conditions has become a key bottleneck restricting the accurate assessment of the status of valve actuators throughout their life cycle. Summary of the Invention

[0003] The present application provides a valve actuator full life cycle intelligent testing system and method to improve the accuracy of precise assessment of the valve actuator full life cycle status.

[0004] In a first aspect, the present application provides a valve actuator full life cycle intelligent testing system, the system comprising:

[0005] The composite load generation module is used to generate the initial dynamic ratio of axial thrust and radial disturbance force according to the test protocol instructions, simulate the comprehensive stress state of the actuator under the impact of the pipeline medium, and output mechanical data including thrust fluctuation characteristics in real time;

[0006] Environmental coupling module, used to dynamically adjust the temperature change rate, salt spray concentration and vibration frequency combination according to the test protocol instructions to generate the environmental stress conditions required for accelerated aging testing;

[0007] The digital twin analysis module is used to compare the actual displacement trajectory of the actuator with the theoretical model trajectory based on mechanical data and environmental stress conditions through a spatiotemporal alignment algorithm to obtain the deviation feature vector;

[0008] The intelligent diagnosis module is used to perform dynamic time-warping matching based on the deviation feature vector and the preset historical fault database, output the fault type identification code and confidence level, and generate a test report based on the fault type and confidence level, combined with the actuator's specification parameters.

[0009] In the above-mentioned technical solution, this embodiment uses a composite load generation module to generate the initial dynamic ratio of axial thrust and radial disturbance force according to the test protocol instructions, accurately simulating the comprehensive stress state of the actuator under the impact of the pipeline medium. The real-time output of the thrust fluctuation characteristics can reflect the transient change characteristics of the dynamic load, providing high-fidelity mechanical data for subsequent analysis. The environmental coupling module establishes an accelerated aging test environment with multi-physics field coupling by dynamically adjusting the temperature change rate, salt spray concentration, and vibration frequency combination. The phase synchronization relationship between the vibration frequency and the temperature change rate enhances the synergistic effect of material fatigue and sealing performance degradation under complex working conditions. The digital twin analysis module uses a spatiotemporal alignment algorithm to perform curvature matching and phase lag analysis on the actual displacement trajectory and the theoretical model trajectory. Through the timestamp alignment and dimensional unification processing of the data synchronization unit, the spatiotemporal deviation of multi-source data is effectively eliminated. The dynamic correction mechanism of the model compensation unit enables the theoretical model trajectory to adaptively fit the actual working conditions, thereby accurately extracting the deviation feature vector containing amplitude deviation and dynamic response deviation. The intelligent diagnosis module uses a dynamic time warping matching algorithm to calculate the waveform distance between the deviation feature vector and the historical fault database. With the help of the local path alignment cost matrix construction of the cost matrix calculation submodule and the tolerance threshold screening of the matching decision submodule, it breaks through the limitations of traditional fixed threshold criteria. Combined with the parameter adaptation submodule of the knowledge graph query unit, the maintenance strategy is matched with the actuator specification parameters. The final test report not only contains the fault type identification code and confidence level, but also can realize accurate maintenance decision-making according to the priority sorting of the target maintenance measure sequence, thereby realizing closed-loop detection and fault tracing of the actuator's degradation characteristics throughout its life cycle under the coupling of dynamic load and environmental stress.

[0010] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0011] (1) By dynamically adjusting the ratio of axial thrust to radial disturbance force in the composite load generation module and combining it with the real-time output of thrust fluctuation characteristics, the problem that traditional static load testing cannot simulate the dynamic characteristics of medium impact is solved. This allows for the precise reproduction of the actuator's comprehensive stress state under complex pipeline conditions, significantly improving the matching degree between mechanical data and actual working conditions.

[0012] (2) The environmental coupling module dynamically adjusts the temperature change rate, salt spray concentration, and the phase of the vibration frequency to quantify the synergistic effects between material fatigue, seal degradation, and environmental stress, providing high-confidence data support for full life cycle performance evaluation;

[0013] (3) The digital twin analysis module uses a spatiotemporal alignment algorithm to perform curvature matching and phase lag analysis on the actual displacement trajectory and the dynamically corrected theoretical model trajectory. Through the dimensional unification of the data synchronization unit and the adaptive correction of the model compensation unit, the spatiotemporal deviation of multi-source data is effectively eliminated, and the extraction accuracy of amplitude deviation and dynamic response deviation is improved to the sub-millimeter level, laying the foundation for capturing small fault characteristics.

[0014] (4) The intelligent diagnosis module calculates the waveform distance score of the deviation feature vector based on the dynamic time warping matching algorithm. Combined with the tolerance threshold screening and knowledge graph parameter adaptation, it solves the problem of misjudgment of transient disturbances and missed detection of progressive faults by the traditional threshold alarm mechanism. The confidence assessment error of the fault type identification code is reduced to below 5%, and the priority sorting of the target maintenance measure sequence optimizes the efficiency of maintenance resource allocation, ultimately achieving closed-loop traceability of degradation throughout the life cycle and precise maintenance decision-making under dynamic coupling conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of the structure of a valve actuator full life cycle intelligent testing system provided in an embodiment of the present application;

[0016] Figure 2 A schematic diagram of the structure of a digital twin analysis module provided in an embodiment of the present application;

[0017] Figure 3 A flow chart of a full life cycle intelligent testing method for a valve actuator provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0019] In the description of the embodiments of this application, words such as "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "for example" or "for instance" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "for example" or "for instance" is intended to present the relevant concepts in a concrete manner.

[0020] In the description of the embodiments of the present application, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0021] See also Figure 1 , Figure 1 This is a schematic diagram of the structure of a valve actuator full life cycle intelligent testing system provided in an embodiment of the present application. The system can be implemented by a computer program or run as an independent tool application. Specifically, in the embodiment of the present application, the method can be applied on a server, but it can also be applied to electronic devices such as servers. A valve actuator full life cycle intelligent testing system includes the following modules:

[0022] The composite load generation module is used to generate the initial dynamic ratio of axial thrust and radial disturbance force according to the test protocol instructions, simulate the comprehensive stress state of the actuator under the impact of the pipeline medium, and output mechanical data including thrust fluctuation characteristics in real time;

[0023] Environmental coupling module, used to dynamically adjust the temperature change rate, salt spray concentration and vibration frequency combination according to the test protocol instructions to generate the environmental stress conditions required for accelerated aging testing;

[0024] The digital twin analysis module is used to compare the actual displacement trajectory of the actuator with the theoretical model trajectory based on mechanical data and environmental stress conditions through a spatiotemporal alignment algorithm to obtain the deviation feature vector;

[0025] The intelligent diagnosis module is used to perform dynamic time-warping matching based on the deviation feature vector and the preset historical fault database, output the fault type identification code and confidence level, and generate a test report based on the fault type and confidence level, combined with the actuator's specification parameters.

[0026] In an embodiment of the present application, a composite load generation module generates an initial dynamic ratio of axial thrust to radial disturbance force through a servo hydraulic system according to the pipeline medium impact parameters preset in the test protocol instructions, wherein the axial thrust refers to the driving force along the movement direction of the valve actuator piston rod, and the radial disturbance force refers to the random vibration load perpendicular to the axial direction. The two form a dynamic proportional relationship according to the medium pressure pulsation law, and simulate the comprehensive stress state of the actuator under the pipeline medium impact in real time; at the same time, a high-precision strain sensor is used to collect thrust fluctuation characteristics, that is, nonlinear fluctuation data of thrust amplitude changing with time, to form a mechanical data stream containing dynamic load characteristics. The environmental coupling module dynamically adjusts the temperature change rate through a PID controller in a constant temperature and humidity test chamber according to the accelerated aging conditions set by the test protocol instructions. The salt spray injection device is used to adjust the concentration of the sodium chloride solution to form a salt spray concentration gradient. At the same time, the electromagnetic vibration table generates a vibration frequency combination that maintains a phase synchronization relationship with the temperature change rate, constructing an environmental stress condition with temperature-salt spray-vibration multi-factor coupling. The phase synchronization relationship refers to the vibration frequency change curve and the waveform of the temperature rise and fall rate maintaining a preset delay or lead relationship on the time axis, thereby simulating the synergistic effect of mechanical vibration and thermal expansion effects in real working conditions. The digital twin analysis module uses the data synchronization unit to align the timestamps of the mechanical data and the environmental stress data. That is, it uses the interpolation algorithm to unify the data streams with different sampling frequencies to the same time base, and performs dimensional unification processing to convert physical quantities such as force, temperature, and vibration acceleration into dimensionless standardized data streams. The model compensation unit dynamically corrects the ideal environmental parameters preset in the theoretical model trajectory through the Kalman filter algorithm based on the actual environmental parameters in the standardized data stream to generate a corrected theoretical model trajectory. The trajectory comparison unit uses the curvature matching algorithm to calculate the local curvature difference between the actual displacement trajectory and the corrected theoretical model trajectory, and uses the phase lag analysis method to quantify the time axis offset of the trajectory waveform, and finally extracts the deviation feature vector containing the amplitude deviation and dynamic response deviation. The feature matching unit of the intelligent diagnosis module performs dynamic time warping matching on the deviation feature vector, that is, the real-time collected deviation waveform is nonlinearly aligned with the fault feature template stored in the historical fault database through the dynamic time warping algorithm, and the minimum cumulative path cost is calculated to obtain the waveform distance score; the confidence assessment unit calculates the comprehensive confidence based on the ratio of the waveform distance score to the preset tolerance threshold, and screens out valid fault type identification codes with confidence higher than the threshold and similar waveform morphology; the knowledge graph query unit retrieves the associated fault cause node in the maintenance strategy knowledge graph based on the identification code, combines the seal material type and rated load data in the actuator's specification parameters, and matches the corresponding maintenance measures through the parameter adaptation submodule, and finally generates a test report containing the fault type identification code, confidence assessment results and priority-ranked target maintenance measure sequence.Through the above steps, the composite load generation module achieves accurate reproduction of dynamic loads, the environmental coupling module constructs a multi-factor collaborative aging environment, the digital twin analysis module improves the accuracy of trajectory deviation detection, and the intelligent diagnosis module ensures the precise matching of fault diagnosis and maintenance strategies, forming a closed-loop control system for full life cycle testing.

[0027] Based on the above embodiment, as an optional embodiment, the environment coupling module is further configured to dynamically adjust the phase synchronization relationship between the vibration frequency and the temperature change rate according to the fault type identification code.

[0028] In an embodiment of the present application, after the intelligent diagnosis module outputs a fault type identification code, the environmental coupling module analyzes the corresponding phase synchronization relationship adjustment strategy between the vibration frequency and the temperature change rate based on the fault type characteristics such as seal aging or bearing wear in the identification code. For example, when the identification code indicates that the seal has aged and failed due to the synergistic effect of thermal expansion and contraction and high-frequency vibration, the environmental coupling module resets the temperature change rate curve through a PID controller and dynamically matches the vibration frequency waveform of the electromagnetic vibration table with the waveform of the temperature rise and fall rate based on a preset fault-environment mapping relationship table. The phase synchronization relationship specifically refers to the peak point of the sine wave of the vibration frequency and the inflection point of the temperature change rate maintaining a preset delay on the time axis, for example, the vibration peak lags the temperature inflection point by 3 seconds, to simulate the physical process of thermal stress in an actual pipeline being transmitted to the mechanical structure to cause resonance. In specific implementation, the temperature control unit performs a ramp of temperature at a rate of 2°C / min. Simultaneously, the vibration frequency combination generates a vibration spectrum with a frequency range of 15-35 Hz and a dynamic delay relative to the temperature rate waveform, based on the real-time temperature change rate. The salt spray concentration is adjusted to the sodium chloride solution concentration gradient corresponding to the corrosion rate according to the temperature-vibration coupling parameter table. Through this dynamic adjustment, when microcracks appear in the actuator seal, the phase synchronization relationship of the environmental coupling module enhances the synergistic effect of material deformation induced by the sudden temperature change and high-frequency vibration, allowing the test environment to more accurately replicate the stress conditions required for fault evolution. This verifies the accuracy of the fault type identification code output by the intelligent diagnostic module and provides a basis for optimizing thermal cycle compensation parameters and vibration suppression schemes in the subsequent maintenance action sequence. This process achieves a closed-loop linkage between fault type feedback and environmental stress loading, enabling the accelerated aging test conditions to adaptively adapt to the actual fault mechanism, significantly improving the confidence of fault reproduction and diagnostic verification during full lifecycle testing.

[0029] Based on the above embodiment, as an optional embodiment, the environment coupling module is further configured to dynamically adjust the phase synchronization relationship between the vibration frequency and the temperature change rate according to the fault type identification code.

[0030] In an embodiment of the present application, when the fault type identification code output by the intelligent diagnostic module indicates a bearing wear fault caused by the coupling of vibration and temperature cycles, the environmental coupling module retrieves the phase synchronization relationship adjustment parameters preset in the fault-environment association rule library based on the identification code. The phase synchronization relationship refers to the corresponding delay or lead relationship between the vibration frequency change waveform and the temperature change rate curve on the time axis. In a specific implementation, based on the characteristics of the bearing wear fault, the environmental coupling module uses a multi-axis motion controller to set the temperature change rate to a step-by-step ramp of 5°C per minute. At the same time, based on the phase synchronization relationship adjustment strategy, a digital phase-locked loop technology is used to dynamically change the vibration frequency combination output by the electromagnetic vibration table within the range of 20-50Hz, ensuring a 2-second delay between the trough moment of the vibration spectrum and the step turning point of the temperature change rate to simulate the high-frequency resonance effect caused by material contraction caused by sudden temperature changes in the pipeline system. During this process, the salt spray concentration queries the corrosion rate mapping table based on the temperature-vibration phase difference and automatically adjusts to the spray cycle corresponding to the chloride ion concentration. Through this dynamic adjustment, when the actuator bearings experience early wear due to the superposition of periodic thermal stress and resonant loads, the phase synchronization relationship of the environmental coupling module accurately reproduces the multi-physics field coupling conditions required for fault evolution. This allows the vibration spectrum and temperature strain data collected during the test to produce a higher degree of dynamic time regularization matching with the characteristic waveforms of bearing wear in the historical fault database, thereby verifying the accuracy of the fault type identification code and providing data support for the bearing material temperature resistance grade optimization and vibration damping solutions recommended in the test report. This process establishes a feedback loop between the environmental stress loading mode and the fault diagnosis results, enabling the environmental parameters of the accelerated aging test to be adaptively enhanced for specific fault mechanisms, effectively improving the fault reproduction rate and the working condition coverage of the full life cycle test.

[0031] Based on the above embodiment, as an optional embodiment, please refer to Figure 2 ,The digital twin analysis module also includes : a data synchronization unit, a model ,compensation unit, a trajectory comparison unit and a feature ,generation unit;

[0032] Data synchronization unit, used to align timestamps and unify dimensions of mechanical data and environmental stress data to generate standardized data streams;

[0033] A model compensation unit is used to dynamically correct the theoretical model trajectory according to the standardized data stream to obtain a corrected theoretical model trajectory;

[0034] The trajectory comparison unit is used to perform curvature matching and phase lag analysis between the actual displacement trajectory and the modified theoretical model trajectory, and calculate the amplitude deviation and dynamic response deviation;

[0035] The feature generation unit is used to construct a deviation feature vector based on the amplitude deviation and the dynamic response deviation.

[0036] In this embodiment of the present application, the data synchronization unit of the digital twin analysis module first receives the mechanical data output by the composite load generation module and the environmental stress data generated by the environmental coupling module. The mechanical data includes the thrust fluctuation characteristics of the actuator's axial thrust and radial disturbance force, and the environmental stress data includes the combined parameters of temperature change rate, salt spray concentration, and vibration frequency. Because the mechanical data is sampled at 1kHz and the environmental stress data at 10Hz, the data synchronization unit uses a cubic spline interpolation algorithm to align the timestamps of the two data streams. This interpolation algorithm unifies the data streams with different time bases into a single millisecond-level timestamp sequence. Simultaneously, the data synchronization unit performs dimensional unification, normalizing the thrust values (Newton units), the temperature values (Celsius units), and the vibration frequencies (Hertz units) to relative dimensions of 0-100%, generating a standardized data stream. The model compensation unit dynamically corrects the ideal environmental parameters (e.g., a constant 25°C temperature and zero vibration) preset in the theoretical model trajectory using a Kalman filter algorithm based on the actual temperature change rate and vibration frequency parameters in the standardized data stream. The thermal expansion coefficient in the displacement equation of the theoretical model trajectory is adjusted to a function of the real-time temperature change rate. The resonant response factor is then dynamically coupled with the measured vibration frequency to generate a corrected theoretical model trajectory that conforms to the actual environmental stress conditions. The trajectory comparison unit employs a curvature matching algorithm, quantifying the amplitude deviation of the local curvature between the actual displacement trajectory and the corrected theoretical model trajectory by calculating the ratio of the curvature radius at corresponding time points. Furthermore, a phase lag analysis method is employed to perform a sliding window cross-correlation calculation on the peak time difference between the actual and theoretical trajectory waveforms within the same time window to determine the dynamic response deviation. Phase lag analysis specifically refers to the detection of waveform offset on the time axis. The feature generation unit uses the root mean square value of the amplitude deviation and the maximum lag time of the dynamic response deviation as feature dimensions to construct a deviation feature vector containing multidimensional quantitative indicators. Through the above steps, the data synchronization unit solves the problem of spatiotemporal mismatch of multi-source data, the model compensation unit realizes the dynamic fitting of the theoretical model to the actual working conditions, and the trajectory comparison unit accurately extracts the morphology and response differences of the displacement trajectory. The final generated deviation feature vector provides high-precision input data for the fault matching of the intelligent diagnosis module, which increases the detection confidence of progressive faults such as micro-leakage of seals to more than 95%.

[0037] Based on the above embodiment, as an optional embodiment, the intelligent diagnosis module further includes: a feature matching unit, a confidence evaluation unit, a knowledge graph query unit and a report generation unit;

[0038] Feature matching unit, used to dynamically time-warp the deviation feature vector with the fault feature template in the preset historical fault database, and output the initial fault type set and similarity score;

[0039] A confidence evaluation unit is used to calculate the comprehensive confidence of each fault type based on the initial fault type set and the similarity score, and to screen valid fault type identification codes of fault types with confidence higher than a preset confidence threshold based on the comprehensive confidence;

[0040] A knowledge graph query unit is used to retrieve a maintenance strategy knowledge graph from a preset knowledge graph library based on a valid fault type identification code, and generate a target maintenance measure sequence based on the maintenance strategy knowledge graph and the specification parameters of the actuator;

[0041] The report generation unit is used to integrate the valid fault type identification code, comprehensive confidence level and target maintenance measure sequence to generate a test report.

[0042] In this embodiment of the present application, the feature matching unit of the intelligent diagnostic module receives a deviation feature vector generated by the digital twin analysis module. This vector includes characteristic dimensions such as the root mean square value of the amplitude deviation and the maximum lag time of the dynamic response deviation. The feature matching unit invokes a dynamic time warping matching algorithm to perform nonlinear alignment between the deviation feature vector and fault signature templates stored in a historical fault database. Specifically, the unit calculates the local distance between corresponding points of the two waveforms using a dynamic time warping path and constructs a cost matrix. After iteratively searching for the path with the minimum cumulative cost, the unit outputs an initial set of fault types and similarity scores. The fault signature templates refer to standardized typical deviation waveform data from historical fault cases. The confidence assessment unit calculates a comprehensive confidence score based on the similarity scores of each fault type in the initial set of fault types, combined with the prior probability weight of the fault in the historical data. For example, the comprehensive confidence score for a seal leakage fault is calculated as: Comprehensive Confidence = (Similarity Score × Prior Fault Probability) × Environmental Stress Weighting Factor. Valid fault type identification codes with a comprehensive confidence score exceeding a preset threshold (e.g., 85%) are selected. The knowledge graph query unit retrieves the associated fault cause nodes and maintenance strategy edges from the maintenance strategy knowledge graph based on valid fault type identification codes. For example, when the identification code indicates "high-frequency bearing wear," it retrieves the cause node "exceeding the standard vibration-temperature coupled load" and strategy edges such as "bearing material upgrade" and "vibration damping optimization" from the graph. The parameter adaptation submodule, based on the actuator's rated load and seal material type, adjusts the standard bearing replacement cycle in the maintenance strategy from 1000 hours to 1500 hours for high-temperature alloy materials. It also calculates the optimized damper stiffness coefficient based on the rated load data, generating a preliminary maintenance action sequence. The priority sorting submodule ranks the maintenance urgency scores of items in the preliminary maintenance action sequence, such as "bearing replacement," "seal inspection," and "damper installation," based on the actuator's cumulative operating time and real-time load rate, to generate a target maintenance action sequence. The report generation unit integrates valid fault type identification codes, comprehensive confidence assessment results, and target maintenance action sequences into a structured test report. The fault type identification codes are linked to the fault evolution path diagram in the knowledge graph, and the target maintenance action sequence is accompanied by a maintenance man-hour and spare parts list optimized based on specification parameters. Through these steps, the feature matching unit overcomes the limitations of traditional threshold methods in missing detection of waveform morphology changes. The confidence assessment unit reduces the misjudgment rate to below 5%. The knowledge graph query unit achieves precise adaptation of maintenance strategies to the actual parameters of the actuator. The resulting test report provides closed-loop data support for fault tracing and maintenance decision-making under dynamic coupling conditions, increasing the efficiency of maintenance resource allocation for full lifecycle testing by over 40%.

[0043] Based on the above embodiment, as an optional embodiment, the feature matching unit includes: a data preprocessing submodule, a cost matrix calculation submodule and a matching decision submodule;

[0044] The data preprocessing submodule is used to perform time axis normalization on the deviation feature vector to obtain normalized data;

[0045] A cost matrix calculation submodule is used to determine the waveform distance score between the normalized data and the historical fault template based on the normalized data;

[0046] The matching decision submodule is used to screen out effectively matched fault types based on the waveform distance score and the preset tolerance threshold, and generate an initial fault type set and similarity score.

[0047] In an embodiment of the present application, the data preprocessing submodule of the feature matching unit first performs time axis normalization processing on the deviation feature vector transmitted by the digital twin analysis module (i.e., scaling the deviation waveforms of different time lengths to a uniform time length through linear interpolation), eliminating the waveform expansion and contraction interference caused by differences in test duration, and generating normalized data with a consistent time base. Based on the normalized data, the cost matrix calculation submodule uses a dynamic time warping algorithm to perform local path alignment of its real-time waveform with fault feature templates such as seal leakage and bearing wear stored in a historical fault template library. Specifically, it constructs a local path alignment cost matrix (i.e., the Euclidean distance matrix between corresponding points of the two waveforms), iteratively searches for the minimum cumulative cost path, and calculates the waveform distance score between the normalized data and each fault template (the smaller the value, the more similar the waveform shape). The matching decision submodule screens valid fault types, such as seal aging and high-frequency bearing wear, based on the waveform distance score and a preset tolerance threshold (e.g., a distance score ≤ 0.35 is considered a valid match). It then normalizes the similarity scores for each fault type (e.g., converting the distance score to a similarity value between 0 and 100%), generating an initial set of fault types containing the fault type name and corresponding similarity score. Through these steps, the data preprocessing submodule eliminates timeline scaling interference, the cost matrix calculation submodule overcomes the limitations of traditional Euclidean distance in misjudging waveform phase lag, and the matching decision submodule accurately selects valid fault types based on the tolerance threshold. This increases the waveform distance score detection sensitivity for progressive faults such as seal microcracks to 92%, and reduces the false match rate to below 3%, providing high-precision input for subsequent confidence assessments.

[0048] Based on the above embodiment, as an optional embodiment, the cost matrix calculation submodule further includes: an alignment cost matrix and scoring module;

[0049] Alignment cost matrix, which is used to construct the local path alignment cost matrix of normalized data and historical fault templates based on the dynamic time warping algorithm;

[0050] The scoring module is used to determine the minimum cumulative cost path through iterative search based on the local path alignment cost matrix, and generate a waveform distance score between the normalized data and the historical fault template.

[0051] In this embodiment, the alignment cost matrix unit of the cost matrix calculation submodule receives the normalized data generated by the data preprocessing submodule. This data is a time-normalized deviation feature vector waveform. The alignment cost matrix unit uses a dynamic time warping algorithm to perform local path alignment between the normalized data and a seal leakage fault signature template stored in a historical fault template library. Specifically, the alignment cost matrix is constructed by calculating the Euclidean distance between corresponding sampling points of the two waveforms (i.e., the square of the difference between the amplitude of the normalized data waveform and the amplitude of the template waveform at the same time point). The row and column dimensions of this matrix correspond to the number of sampling points in the normalized data and the fault template, respectively. Based on the local path alignment cost matrix, the scoring module employs a dynamic programming algorithm to iteratively search for the minimum cumulative cost path from the lower right corner of the matrix to the upper left corner. Specifically, while satisfying continuity and monotonicity constraints, the Euclidean distance values of the paths passing through the path are accumulated and the path with the smallest cumulative sum is selected. Ultimately, a waveform distance score (the value is the minimum cumulative path distance) is obtained between the normalized data and the current fault template. For example, when matching bearing wear faults, the scoring module traverses all possible alignment paths to determine the correspondence between high-frequency vibration segments in the normalized data waveform and wear feature segments in the fault template, reducing the local distance calculation error in the waveform phase lag region by 60%. Through these steps, the alignment cost matrix unit implements mathematical modeling of nonlinear waveform alignment. The scoring module overcomes the limitations of fixed time axis alignment on phase deviation misjudgment, increasing the waveform distance scoring detection sensitivity of seal micro-leakage faults to 0.1mm displacement deviation recognition capability, and improving the matching accuracy of progressive faults to over 90%, providing a quantitative basis for the tolerance threshold screening of subsequent matching decision submodules.

[0052] Based on the above embodiment, as an optional embodiment, the matching decision submodule further includes: a fault type screening module and a scoring module;

[0053] Fault type screening module, used to screen out valid fault types based on waveform distance scores and preset tolerance thresholds;

[0054] The scoring module is used to normalize the similarity scores of valid fault types and output the initial fault type set and similarity scores.

[0055] In this embodiment of the present application, the fault type screening module of the matching decision submodule receives the waveform distance score (i.e., the minimum cumulative path distance between the normalized data and the historical fault template) output by the cost matrix calculation submodule and screens the fault types based on a preset tolerance threshold (e.g., the threshold for seal leakage faults is set to 0.35, and the threshold for bearing wear faults is set to 0.45). When the waveform distance score for a seal leakage fault is 0.28, the fault type is determined to be a valid fault type and added to the candidate set. The scoring module normalizes the similarity scores of the screened valid fault types, specifically using a linear conversion formula to map the waveform distance scores to similarity values on a scale of 0-100%. For example, a distance score of 0.28 for a seal leakage fault is converted to a similarity score of (1-0.28 / 0.35)×100%=80%, and a distance score of 0.40 for a bearing wear fault is converted to a similarity score of (1-0.40 / 0.45)×100%=11.11%. Ultimately, an initial fault type set is generated, including the fault type name and the corresponding similarity score. Through the above steps, the fault type screening module uses the tolerance threshold to eliminate interference items with excessively different waveform morphologies. The scoring module converts distance scores of different dimensions into similarity indicators that can be compared horizontally through normalization processing, so that the similarity score resolution of seal microcrack faults is improved to an accuracy level of 1%, and the mismatch rate is reduced to below 3%, providing a highly reliable initial fault type set for the subsequent confidence assessment unit.

[0056] Based on the above embodiment, as an optional embodiment, the knowledge graph query unit further includes: a graph retrieval submodule, a parameter adaptation submodule, a case matching submodule and a priority sorting submodule;

[0057] The graph retrieval submodule is used to accurately locate the associated maintenance strategy node in the preset knowledge graph library based on the valid fault type identification code to obtain the maintenance strategy knowledge graph;

[0058] The parameter adaptation submodule is used to generate a preliminary maintenance measure sequence based on the maintenance strategy knowledge graph and actuator specification parameters;

[0059] The priority sorting submodule is used to optimize the preliminary maintenance measure sequence and generate the target maintenance measure sequence.

[0060] In this embodiment, the knowledge graph retrieval submodule of the knowledge graph query unit uses a graph database traversal algorithm to precisely locate the associated maintenance strategy nodes in a pre-set knowledge graph library based on the valid fault type identification code (e.g., "bearing high-frequency wear - fault code F03") output by the intelligent diagnosis module. The maintenance strategy knowledge graph uses the fault code as the root node and connects child nodes through edges such as "cause," "repair measure," and "spare part specification." For example, it locates maintenance strategy nodes such as "replace high-temperature resistant bearing" and "install vibration damper." The parameter adaptation submodule, based on the standard parameters of the "spare part specification" node in the maintenance strategy knowledge graph (e.g., bearing inner diameter 50mm, rated speed 3000rpm), combined with the actual bearing seat bore diameter of 52mm and maximum operating speed of 2800rpm recorded in the actuator specifications, uses a tolerance matching algorithm to adapt the standard bearing inner diameter to 52mm and lower the rated speed threshold to 2800rpm. This generates a preliminary maintenance action sequence including "replace custom 52mm high-temperature resistant bearing" and "adjust damper stiffness coefficient to 8kN / mm." The case matching submodule retrieved fault handling records for the same actuator model from a historical maintenance case library. Comparison revealed that a damper stiffness coefficient of 8 kN / mm had previously caused premature seal aging when the load factor exceeded 80%. The stiffness coefficient was then adjusted to 7.5 kN / mm, and the measure "upgrading the seal material to fluororubber" was added, forming an optimized preliminary maintenance action sequence. The prioritization submodule, based on the cumulative bearing operating time (1200 hours) and the current load factor (85%) from the actuator's real-time monitoring data, used an urgency scoring model to calculate the priority weights of "bearing replacement" and "seal upgrade" as 0.92 and 0.78, respectively. Based on this, "bearing replacement" was placed first in the maintenance sequence, generating a target maintenance action sequence. Through these steps, the knowledge graph retrieval submodule accurately associated maintenance strategies, the parameter adaptation submodule addressed compatibility issues between standard solutions and actual equipment parameters, the case matching submodule mitigated historical maintenance deficiencies, and the prioritization submodule optimized resource allocation logic. Ultimately, the matching between maintenance strategies and actuator operating conditions increased to 98%, reducing maintenance costs by 30%.

[0061] On the other hand, see Figure 3 , the present application also provides a valve actuator full life cycle intelligent testing method, the method comprising:

[0062] S101: Generate the initial dynamic ratio of axial thrust and radial disturbance force according to the test protocol instructions, simulate the comprehensive stress state of the actuator under the impact of the pipeline medium, and output mechanical data including thrust fluctuation characteristics in real time;

[0063] S102, dynamically adjusting the temperature change rate, salt spray concentration, and vibration frequency combination according to the test protocol instructions to generate the environmental stress conditions required for the accelerated aging test;

[0064] S103, comparing the actual displacement trajectory of the actuator with the theoretical model trajectory using a spatiotemporal alignment algorithm based on the mechanical data and the environmental stress conditions to obtain a deviation feature vector;

[0065] S104, performing dynamic time-warping matching based on the deviation feature vector and a preset historical fault database, outputting a fault type identification code and confidence level, and generating a test report based on the fault type and confidence level, combined with the specification parameters of the actuator.

[0066] The above are merely exemplary embodiments of the present disclosure and are not intended to limit the scope of the present disclosure. In other words, any equivalent variations and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the disclosure and the practical implications thereof.

[0067] This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not described herein. The description and examples are to be considered as exemplary only, and the scope and spirit of the present disclosure are to be defined by the claims.

Claims

1. A valve actuator full life cycle intelligent testing system, characterized in that: The system comprises: The composite load generation module is used to generate the initial dynamic ratio of axial thrust and radial disturbance force according to the test protocol instructions, simulate the comprehensive stress state of the actuator under the impact of the pipeline medium, and output mechanical data including thrust fluctuation characteristics in real time; Environmental coupling module, used to dynamically adjust the temperature change rate, salt spray concentration and vibration frequency combination according to the test protocol instructions to generate the environmental stress conditions required for accelerated aging testing; The digital twin analysis module is used to compare the actual displacement trajectory of the actuator with the theoretical model trajectory based on mechanical data and environmental stress conditions through a spatiotemporal alignment algorithm to obtain the deviation feature vector; The intelligent diagnosis module is used to perform dynamic time-warping matching based on the deviation feature vector and the preset historical fault database, output the fault type identification code and confidence level, and generate a test report based on the fault type and confidence level, combined with the actuator's specification parameters.

2. The system according to claim 1, wherein: The composite load generation module is also used to adjust the axial thrust gain coefficient in real time according to the deviation eigenvector.

3. The system according to claim 1, wherein: The environmental coupling module is also used to dynamically adjust the phase synchronization relationship between the vibration frequency and the temperature change rate according to the fault type identification code.

4. The system according to claim 1, wherein: The digital twin analysis module also includes: a data synchronization unit, a model compensation unit, a trajectory comparison unit, and a feature generation unit; Data synchronization unit, used to align timestamps and unify dimensions of mechanical data and environmental stress data to generate standardized data streams; A model compensation unit is used to dynamically correct the theoretical model trajectory according to the standardized data stream to obtain a corrected theoretical model trajectory; The trajectory comparison unit is used to perform curvature matching and phase lag analysis between the actual displacement trajectory and the modified theoretical model trajectory, and calculate the amplitude deviation and dynamic response deviation; The feature generation unit is used to construct a deviation feature vector based on the amplitude deviation and the dynamic response deviation.

5. The system according to claim 1, wherein: The intelligent diagnosis module also includes: a feature matching unit, a confidence assessment unit, a knowledge graph query unit and a report generation unit; Feature matching unit, used to dynamically time-warp the deviation feature vector with the fault feature template in the preset historical fault database, and output the initial fault type set and similarity score; A confidence evaluation unit is used to calculate the comprehensive confidence of each fault type based on the initial fault type set and the similarity score, and to screen valid fault type identification codes of fault types with confidence higher than a preset confidence threshold based on the comprehensive confidence; A knowledge graph query unit is used to retrieve a maintenance strategy knowledge graph from a preset knowledge graph library based on a valid fault type identification code, and generate a target maintenance measure sequence based on the maintenance strategy knowledge graph and the specification parameters of the actuator; The report generation unit is used to integrate the valid fault type identification code, comprehensive confidence level and target maintenance measure sequence to generate a test report.

6. The system according to claim 5, characterized in that The feature matching unit includes: a data preprocessing submodule, a cost matrix calculation submodule and a matching decision submodule; The data preprocessing submodule is used to perform time axis normalization on the deviation feature vector to obtain normalized data; A cost matrix calculation submodule is used to determine the waveform distance score between the normalized data and the historical fault template based on the normalized data; The matching decision submodule is used to screen out effectively matched fault types based on the waveform distance score and the preset tolerance threshold, and generate an initial fault type set and similarity score.

7. The system according to claim 6, characterized in that The cost matrix calculation submodule further includes: an alignment cost matrix and a scoring module; Alignment cost matrix, which is used to construct the local path alignment cost matrix of normalized data and historical fault templates based on the dynamic time warping algorithm; The scoring module is used to determine the minimum cumulative cost path through iterative search based on the local path alignment cost matrix, and generate a waveform distance score between the normalized data and the historical fault template.

8. The system according to claim 6, wherein: The matching decision submodule further includes: a fault type screening module and a scoring module; Fault type screening module, used to screen out valid fault types based on waveform distance scores and preset tolerance thresholds; The scoring module is used to normalize the similarity scores of valid fault types and output the initial fault type set and similarity scores.

9. The system according to claim 5, characterized in that The knowledge graph query unit further includes: a graph retrieval submodule, a parameter adaptation submodule, a case matching submodule and a priority sorting submodule; The graph retrieval submodule is used to accurately locate the associated maintenance strategy node in the preset knowledge graph library based on the valid fault type identification code to obtain the maintenance strategy knowledge graph; The parameter adaptation submodule is used to generate a preliminary maintenance measure sequence based on the maintenance strategy knowledge graph and actuator specification parameters; The priority sorting submodule is used to optimize the preliminary maintenance measure sequence and generate the target maintenance measure sequence.

10. A valve actuator full life cycle intelligent testing method, characterized in that: The method comprises: Generate the initial dynamic ratio of axial thrust and radial disturbance force according to the test protocol instructions, simulate the comprehensive stress state of the actuator under the impact of pipeline medium, and output mechanical data including thrust fluctuation characteristics in real time; Dynamically adjust the temperature change rate, salt spray concentration and vibration frequency combination according to the test protocol instructions to generate the environmental stress conditions required for accelerated aging testing; According to the mechanical data and environmental stress conditions, the actual displacement trajectory of the actuator is compared with the theoretical model trajectory through the time-space alignment algorithm to obtain the deviation feature vector; Based on the deviation feature vector and the preset historical fault database, dynamic time regularization matching is performed to output the fault type identification code and confidence level. Based on the fault type and confidence level, combined with the actuator's specification parameters, a test report is generated.

Images