Combined displacement sensing method and platform for oil cylinder

Abstract

The present invention discloses a joint displacement sensing method and platform for a cylinder, and relates to the field of displacement measurement technology, including: performing a self-check of a joint sensor group, and if the self-check passes, performing a reference zero point correction; activating the joint sensor group to establish a real-time displacement result and an additional data set; obtaining the real-time control parameters of the cylinder and performing parameter analysis, inputting the parameter analysis results and the additional data set into a joint authentication network, performing a joint authentication of the cylinder working state, and establishing an authentication influence coefficient; inputting the additional data set and the real-time displacement result into a displacement background correction network, performing displacement correction of the real-time displacement result, and generating a displacement correction result; establishing an authentication risk based on the authentication influence coefficient, performing a displacement correction result compensation mark, and generating a displacement monitoring result based on the compensation mark result. The present invention solves the technical problem of insufficient accuracy of the hydraulic cylinder displacement sensing method in the prior art, and achieves the technical effect of improving the accuracy of cylinder displacement measurement.

Description

Technical Field

[0001] The present invention relates to the technical field of displacement measurement, and in particular to a combined displacement sensing method and platform for an oil cylinder. Background Art

[0002] In the field of modern industry and mechanical engineering, hydraulic systems are widely used in various heavy machinery, engineering vehicles and automation equipment. As a key component of the hydraulic system, the performance of the hydraulic cylinder directly affects the operating efficiency and reliability of the entire system. In order to ensure the precise control and safe operation of the hydraulic cylinder, it is particularly important to monitor its displacement state in real time. However, traditional displacement sensing technology has the problem of insufficient accuracy and is difficult to meet the precise measurement requirements under complex working conditions. Summary of the invention

[0003] The present application provides a combined displacement sensing method and platform for an oil cylinder, which is used to solve the technical problem of insufficient accuracy of the displacement sensing method of the hydraulic oil cylinder in the prior art.

[0004] In view of the above problems, the present application provides a combined displacement sensing method and platform for a cylinder.

[0005] In a first aspect of the present application, a combined displacement sensing method for a cylinder is provided, the method comprising:

[0006] Start the central processing unit of the joint displacement sensing system, perform a self-check of the joint sensor group, and if the self-check result is a passing result, perform a reference zero point correction on the joint sensor group; activate the displacement sensor of the joint sensor group, perform displacement data recording of the cylinder piston, and establish a real-time displacement result; activate the pressure sensor, temperature sensor, and vibration sensor of the linkage sensor, perform linkage data acquisition through the pressure sensor, temperature sensor, and vibration sensor, and establish an additional data set; obtain the real-time control parameters of the cylinder, perform parameter analysis on the real-time control parameters, input the parameter analysis results and the additional data set into the joint authentication network, perform joint authentication of the cylinder working status, and establish an authentication influence coefficient; input the additional data set and the real-time displacement result into the displacement background correction network, perform displacement correction of the real-time displacement result, and generate a displacement correction result; establish an authentication risk based on the authentication influence coefficient, perform a displacement correction result compensation mark based on the authentication risk, and generate a displacement monitoring result based on the compensation mark result.

[0007] A second aspect of the present application provides a combined displacement sensing platform for a cylinder, the platform comprising:

[0008] A sensor self-check module, wherein the sensor self-check module starts the central processing unit of the joint displacement sensor system, performs a self-check of the joint sensor group, and if the self-check result is a passing result, the joint sensor group is subjected to a reference zero point correction; a displacement data recording module, wherein the displacement data recording module activates the displacement sensor of the joint sensor group, performs displacement data recording of the oil cylinder piston, and establishes a real-time displacement result; a linkage data acquisition module, wherein the linkage data acquisition module activates the pressure sensor, temperature sensor, and vibration sensor of the linkage sensor, performs linkage data acquisition through the pressure sensor, temperature sensor, and vibration sensor, and establishes an additional data set; a joint authentication module, wherein the joint authentication module obtains the real-time control parameters of the oil cylinder, performs parameter analysis on the real-time control parameters, inputs the parameter analysis results and the additional data set into the joint authentication network, performs joint authentication of the working state of the oil cylinder, and establishes an authentication influence coefficient; a displacement correction module, wherein the displacement correction module inputs the additional data set and the real-time displacement result into the displacement background correction network, performs displacement correction of the real-time displacement result, and generates a displacement correction result; a compensation identification module, wherein the compensation identification module establishes an authentication risk based on the authentication influence coefficient, performs a compensation identification of the displacement correction result based on the authentication risk, and generates a displacement monitoring result based on the compensation identification result.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] The present application starts the central processing unit of the joint displacement sensing system, performs a self-test of the joint sensor group, and if the self-test result is a passing result, performs a reference zero point correction on the joint sensor group; activates the displacement sensor of the joint sensor group, performs displacement data recording of the cylinder piston, and establishes a real-time displacement result; activates the pressure sensor, temperature sensor, and vibration sensor of the linkage sensor, performs linkage data collection through the pressure sensor, temperature sensor, and vibration sensor, and establishes an additional data set; obtains the real-time control parameters of the cylinder, performs parameter analysis on the real-time control parameters, inputs the parameter analysis results and the additional data set into the joint authentication network, performs joint authentication of the cylinder working status, and establishes an authentication influence coefficient; inputs the additional data set and the real-time displacement result into the displacement background correction network, performs displacement correction of the real-time displacement result, and generates a displacement correction result; establishes an authentication risk based on the authentication influence coefficient, performs a displacement correction result compensation mark based on the authentication risk, and generates a displacement monitoring result based on the compensation mark result. The present invention solves the technical problem of insufficient accuracy of the hydraulic cylinder displacement sensing method in the prior art, by starting a central processing unit, performing self-checking and zero-point correction, activating sensors to record data, establishing additional data sets, parsing control parameters and performing state authentication, inputting a correction network to generate correction results, establishing authentication risks and compensation identification, and finally generating displacement monitoring results, thereby achieving the technical effect of improving the cylinder displacement measurement accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic flow chart of a combined displacement sensing method for a cylinder provided in an embodiment of the present application;

[0013] Figure 2 A schematic diagram of the structure of a combined displacement sensing platform for a cylinder provided in an embodiment of the present application.

[0014] Explanation of the reference numerals: sensor self-check module 11 , displacement data recording module 12 , linkage data acquisition module 13 , joint authentication module 14 , displacement correction module 15 , compensation identification module 16 . DETAILED DESCRIPTION

[0015] The present application provides a combined displacement sensing method and platform for an oil cylinder, and aims to solve the technical problem of insufficient accuracy of the displacement sensing method of the hydraulic oil cylinder in the prior art. By starting the central processing unit, performing self-test and zero-point correction, activating the sensor to record data, establishing an additional data set, parsing the control parameters and performing status authentication, inputting the correction result into the correction network, establishing authentication risks and compensation identification, and finally generating the displacement monitoring result, the technical effect of improving the displacement measurement accuracy of the oil cylinder is achieved.

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0017] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, platform, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0018] Embodiment 1, as Figure 1 As shown, the present application provides a combined displacement sensing method for a cylinder, the method comprising:

[0019] Step A100: Start the central processing unit of the joint displacement sensor system and perform a self-test of the joint sensor group. If the self-test result is a passing result, the joint sensor group will be subjected to a reference zero point calibration.

[0020] In the embodiment of the present application, after starting the central processing unit (CPU) of the joint displacement sensing system, it first enters the initialization phase to check the normal status of basic system functions, such as power supply, memory and communication interface. Then the CPU loads the pre-written self-test program and sends a self-test instruction to the joint sensor group (including displacement sensor, pressure sensor, temperature sensor and vibration sensor). Each sensor executes the self-test program in turn, for example, the displacement sensor moves to a predetermined reference position, collects the current displacement data and compares it with the reference value; the pressure sensor applies a known standard pressure, reads the current pressure value and compares it with the standard value; the temperature sensor is exposed to a known temperature environment, reads the temperature and compares it with the known temperature; the vibration sensor is subjected to vibration of known frequency and amplitude, reads the vibration data and compares it with the preset standard. After that, the self-test data of all sensors are fed back to the CPU, which summarizes and analyzes these data. If all data are within the normal range, the self-test is considered to have passed. After the self-test passes, the CPU sends a reference zero point correction instruction to the sensor group, and the sensor group performs zero point correction to adjust all initial readings to zero to ensure the accuracy of subsequent data collection.

[0021] Step A200: Activate the displacement sensor of the joint sensor group, execute displacement data recording of the cylinder piston, and establish real-time displacement results.

[0022] In an embodiment of the present application, after activating the displacement sensor of the joint sensor group, the displacement data recording of the cylinder piston begins. The displacement sensor is a device used to measure the position change of the cylinder piston. Through the high-precision detection capability of the sensor, every tiny movement of the piston in the cylinder is captured in real time. When the displacement sensor is activated, it begins to continuously monitor the position changes of the piston and record these changes as data points. These data points reflect the position of the piston at different points in time, forming a complete displacement data record. As the piston moves, the displacement sensor updates the data in real time, stores the real-time collected data, and establishes a real-time displacement result.

[0023] Step A300: activating the pressure sensor, temperature sensor, and vibration sensor of the linkage sensor, performing linkage data collection through the pressure sensor, temperature sensor, and vibration sensor, and establishing an additional data set.

[0024] In the embodiment of the present application, while activating the displacement sensor, the pressure sensor, temperature sensor, and vibration sensor of the linkage sensor are activated and start to work together. Through linkage data collection, their respective measurement data are obtained respectively, and the data collected by each are integrated to establish an additional data set.

[0025] Step A400: Acquire the real-time control parameters of the oil cylinder, perform parameter analysis on the real-time control parameters, input the parameter analysis results and additional data sets into the joint authentication network, perform joint authentication of the oil cylinder working status, and establish an authentication influence coefficient.

[0026] In an embodiment of the present application, the real-time control parameters of the oil cylinder are first collected in real time through the sensor group and the controller, and then the Kalman filter algorithm is used to smooth the collected control parameters to remove noise and improve data accuracy. After the parameter analysis is completed, the analysis results are integrated with the additional data set previously collected by the linkage sensor. During the data integration process, weighted averaging and principal component analysis techniques are used to fuse and reduce the dimension of data from different sensors. The weighted average integrates the pressure, temperature and vibration data to form an additional data set; PCA technology is used for dimensionality reduction, extracts key features, and reduces redundant information.

[0027] Next, the parsing results and additional data sets are input into the joint certification network. The joint certification network is an intelligent system that integrates multiple data analysis and verification algorithms. It uses deep learning convolutional neural networks for preliminary feature extraction and pattern recognition, and then classifies and verifies through support vector machines to evaluate whether the working status of the oil cylinder meets expectations and identify potential risks and anomalies. The establishment of the joint certification network relies on deep learning and machine learning algorithms. Its architecture uses convolutional neural networks for preliminary feature extraction and combines support vector machines for classification and verification. Specifically, in the convolution layer, multi-layer convolution operations are performed on the input data to extract high-dimensional features; in the pooling layer, feature dimensionality reduction is performed to retain important information and reduce the amount of calculation; in the fully connected layer, the features extracted by the convolution layer and the pooling layer are integrated to form a feature vector; finally, SVM is used for classification and verification to determine the working status of the oil cylinder.

[0028] The training data of the joint certification network comes from historical operating data and experimental data, covering pressure, temperature, vibration and displacement data under various working conditions. The training process adopts a supervised learning method to train the model through annotated historical data. Specifically, the historical data is first cleaned and normalized to remove noise and outliers; the data is divided into a training set and a validation set to ensure the generalization ability of the model; the CNN and SVM models are optimized through the back propagation algorithm and the gradient descent method; the model is evaluated using the validation set, and the model parameters are adjusted to improve the accuracy and robustness of the model.

[0029] Through comprehensive analysis of the joint authentication network, an authentication influence coefficient is generated. This coefficient is obtained by weighted average method. Specifically, the data of each sensor is first standardized so that they can be compared on the same dimension; then, the standardized data is weighted averaged according to the pre-set weights of each sensor to generate the authentication influence coefficient.

[0030] Furthermore, in the method provided in the embodiment of the application, the real-time control parameters are parsed, the parameter parsing results and the additional data set are input into the joint authentication network, and the joint authentication of the cylinder working status is performed, and the method also includes:

[0031] The data of the cylinder is collected through the data collection unit to establish a historical working data set; a digital twin model of the cylinder is established according to the historical working data set and the attribute information of the cylinder, and a control parameter working condition simulation is performed based on the digital twin model, and the model parameters of the digital twin model are updated according to the simulation results; the parameter analysis results are synchronized to the digital twin model of the updated model parameters, and the real-time simulation results of the digital twin model are fed back to the joint authentication network; and the joint authentication network is used to perform a joint authentication of the cylinder working status based on the real-time simulation results and the additional data set.

[0032] In the embodiment of the present application, data acquisition is performed on the cylinder through a data acquisition unit to collect data such as pressure, temperature, displacement and vibration of the cylinder under various working conditions in real time, and the data are stored in a database to form a historical working data set.

[0033] Next, a digital twin model of the cylinder is constructed using data modeling tools such as MATLAB based on the historical working data set and the cylinder's attribute information, such as physical dimensions, material properties, and design parameters. Based on the digital twin model, control parameter working condition simulation is performed. Various control parameters of the cylinder are simulated and tested in a virtual environment, and working condition simulation is performed using simulation software such as ANSYS to predict the behavior and performance of the cylinder under different conditions. The simulation results are used to update the model parameters of the digital twin model. Specifically, all key data points in each simulation run are collected during the simulation process, including parameters such as pressure, temperature, displacement, and vibration; the simulation results are compared with the actual real-time data collected, the error is calculated, and the accuracy of the model is evaluated using error analysis techniques such as mean square error; the parameters of the model are adjusted based on the results of the error analysis; the above steps are repeated to continuously adjust the model parameters until the simulation results are highly consistent with the actual data. This process is automated by using optimization algorithms such as gradient descent.

[0034] On this basis, the cylinder control parameters acquired in real time are parsed. Parameter parsing refers to filtering, sorting and converting complex raw data into a standardized, easy-to-process format, and parsing it using data processing tools. Then, the parsing results are synchronized to the updated digital twin model. Subsequently, the real-time simulation results and additional data sets of the updated digital twin model are input into the joint certification network. Subsequently, the real-time simulation results and additional data sets of the updated digital twin model are input into the joint certification network.

[0035] Furthermore, in the method provided in the embodiment of the application, the parameter analysis result is synchronized to the digital twin model of the updated model parameters, and the real-time simulation result of the digital twin model is fed back to the joint authentication network, and further includes:

[0036] The continuous working time of the oil cylinder is obtained, and a pre-response window is established based on the continuous working time; the pre-working data is called through the pre-response window, an impact evaluation of the pre-working state is performed, and a pre-working state impact evaluation result is established; and the digital twin model is initialized and managed according to the pre-working state impact evaluation result.

[0037] In the embodiment of the present application, the operation time of the oil cylinder is first recorded by the time sensor and the control unit to obtain the continuous working time of the oil cylinder. The continuous working time refers to the cumulative working time of the oil cylinder from start to stop. The sensor records the start time when the oil cylinder starts, and records the stop time when the oil cylinder stops. The central control unit calculates the difference between the start and stop time to obtain the working time of each operation cycle, and accumulates these time durations to form continuous working time data.

[0038] Next, the historical working data is analyzed using regression analysis and cluster analysis techniques. The historical working data of the cylinder is extracted from the database through the data acquisition unit, including parameters such as pressure, temperature, displacement and vibration. Using regression analysis technology, the trend of each parameter over time is analyzed to identify the key influencing factors. Using cluster analysis technology, the data is grouped to identify typical behavior patterns and potential risks under different working conditions. Based on the results of historical data analysis, a pre-response window is set. The pre-response window is a time interval used for early intervention and monitoring of the working status of the cylinder. By analyzing historical data, the time period when the cylinder is most likely to have problems under different continuous working times is determined. For example, if the data shows that the cylinder is prone to problems after 8 hours of continuous work, set the pre-response window to between 7.5 hours and 8.5 hours.

[0039] In the pre-response window, call historical work data and real-time collected data to evaluate the impact of the pre-work status. In the pre-response window, use sensors to monitor the working status of the oil cylinder in real time and collect current operating data. Call historical work data, compare and analyze with current data, and identify key factors that may affect the operation of the oil cylinder. Use regression analysis and cluster analysis techniques to evaluate the impact of the pre-work status and identify potential risks and abnormal situations. Use regression analysis technology to evaluate the key influencing factors in historical and current data and quantify their impact. Use cluster analysis technology to identify potential risks and abnormal situations by analyzing pre-work data. Generate pre-work status impact evaluation results based on the analysis results.

[0040] According to the results of the previous working state impact evaluation, the digital twin model is initialized and managed and parameters are adjusted. Specifically, all key data points in the previous response window are first collected, including parameters such as pressure, temperature, displacement and vibration. Then an error analysis is performed to compare the previous working state impact evaluation results with the actual collected real-time data, and the error is calculated using the mean square error technique. According to the error analysis results, an optimization algorithm such as the gradient descent method is used to adjust the parameters of the digital twin model. For example, if the evaluation results show that certain parameters have a greater impact on the stability of the cylinder, the model needs to increase the weights of these parameters. Repeat the above steps and continue to adjust the model parameters until the model can highly accurately reflect the current state of the cylinder.

[0041] Through the above steps, the initialization management of the digital twin model is completed.

[0042] Furthermore, in the method provided in the embodiment of the application, the preceding work data is called through the preceding response window to perform an impact evaluation of the preceding work status, and a preceding work status impact evaluation result is established, and further includes:

[0043] S1: configuring a timing attenuation factor based on the preceding response window; S2: performing a load analysis on the preceding work data to establish a timing load evaluation result; S3: performing load compensation on the timing load evaluation result according to the timing attenuation factor to establish a first preceding work state impact evaluation result; S4: performing a load fluctuation evaluation on the preceding work data to establish a second preceding work state impact evaluation result based on the load fluctuation evaluation result and the timing attenuation factor; S5: establishing a preceding work state impact evaluation result based on the first preceding work state impact evaluation result and the second preceding work state impact evaluation result.

[0044] In an embodiment of the present application, firstly, the historical data in the pre-response window is analyzed by the timing analysis technology to configure the timing attenuation factor, which is used to quantify the attenuation effect of time on the load. Specifically, the relevant data in the pre-response window is extracted from the historical working data set, and the changing trend of the data over time is analyzed using timing analysis technology, such as exponential smoothing. Then, statistical analysis software is used to perform exponential smoothing to obtain a smooth curve of the data, and the mode of data attenuation over time is determined based on the smooth curve. According to the analysis results, the timing attenuation factor is configured. For example, for the case of gradual attenuation, the attenuation factor is configured to 0.9, which means that the impact is reduced by 10% for every time unit.

[0045] Next, load analysis techniques are used to evaluate the load characteristics in the pre-operation data and establish the time series load evaluation results. In this process, the pre-operation data, including parameters such as pressure, temperature, displacement and vibration, are first extracted from the pre-response window, and the relevant data is extracted from the database using SQL queries. Load analysis techniques such as Fourier transform are used to evaluate the load characteristics in the data. Fourier transform is performed using Python's SciPy library to identify the frequency components in the data, and the frequency components are analyzed to determine the size and change trend of the load. Based on the analysis results, the time series load evaluation results are established to quantify the changes in the load over time.

[0046] Then, the load compensation is performed on the time series load evaluation result according to the configured time series attenuation factor to establish the first pre-working state impact evaluation result. Load compensation refers to adjusting the time series load evaluation result according to the configured time series attenuation factor. For example, when the attenuation factor is 0.9, the load value of each time unit is multiplied by an exponential attenuation factor of 0.9 for adjustment. The compensated load data is used to save and process the adjusted load data using a data processing tool to generate a preliminary impact evaluation result.

[0047] Subsequently, the load fluctuation analysis technology is used to evaluate the load fluctuation characteristics in the previous work data, and the second previous work state impact evaluation result is established by combining the time series attenuation factor. Specifically, when performing load fluctuation analysis, the load fluctuation characteristics in the data are evaluated by using the standard deviation analysis technology to identify the fluctuation amplitude and frequency. The standard deviation of the data is calculated using Python's NumPy library to quantify the load fluctuation amplitude. Next, the load fluctuation evaluation results are combined with the time series attenuation factor to adjust the fluctuation impact, and the adjusted fluctuation data is obtained by calculating the attenuation adjustment of the fluctuation data. Based on the adjusted load fluctuation data, the adjusted fluctuation data is saved and processed using a data processing tool to generate the impact evaluation results of the second step.

[0048] Finally, the first and second pre-working state impact evaluation results are combined to establish the final pre-working state impact evaluation result. When combining the first pre-working state impact evaluation result and the second pre-working state impact evaluation result, the two results are combined by using a weighted average method, in which the two evaluation results have the same weight.

[0049] Step A500: input the additional data set and the real-time displacement result into a displacement background correction network, perform displacement correction on the real-time displacement result, and generate a displacement correction result.

[0050] In an embodiment of the present application, the additional data set and the real-time displacement result are input into the displacement background correction network, and the displacement correction of the real-time displacement result is performed. The displacement background correction network is a pre-constructed network. When constructing it, a large amount of pressure, temperature, vibration and displacement data covering various working conditions are first extracted from the historical working data set, and these data are used as training data. After that, a neural network model is used for training. The neural network model learns the complex relationship between the input data and the displacement correction through multi-layer nonlinear mapping. The training process includes forward propagation and back propagation, and the error between the predicted value and the actual value is minimized by continuously adjusting the model parameters such as weights and biases. The pre-processed additional data set and the historical displacement results are used as input data, and the actually measured historical displacement data are used as the target output. Through the neural network training, the model gradually optimizes the parameters through multiple iterations so that it can accurately correct the real-time displacement data.

[0051] By inputting the additional data set collected in real time and the real-time displacement results into the trained neural network model, the neural network model corrects the real-time displacement data through multi-layer nonlinear mapping, outputs the corrected displacement data, and obtains the displacement correction result.

[0052] Step A600: establishing an authentication risk based on the authentication influence coefficient, performing a compensation mark on a displacement correction result based on the authentication risk, and generating a displacement monitoring result based on the compensation mark result.

[0053] In the embodiment of the present application, based on the certification impact coefficient, the certification risk is established by comparing with the preset risk table. The preset risk table corresponds different ranges of certification impact coefficients to different risk levels. For example, when the certification impact coefficient is less than 0.3, it is low risk, when it is between 0.3 and 0.7, it is medium risk, and when it is greater than or equal to 0.7, it is high risk. The calculated certification impact coefficient is compared with the risk table to determine the risk level of the oil cylinder.

[0054] Next, compensation marks are made for the displacement correction results based on the certification risk. The compensation mark is to adjust and correct the cylinder displacement data to ensure the accuracy and reliability of the data. Specifically, the corresponding displacement correction strategy is first selected according to the level of certification risk. For low-risk situations, a linear regression algorithm is applied for displacement correction. By establishing a linear relationship between sensor data and actual displacement, the deviation is calculated and corrected, and the sensor data is smoothed, such as using a simple moving average method to reduce the impact of short-term fluctuations. For medium-risk situations, a weighted moving average method is applied for data smoothing, giving the latest data a higher weight to enhance real-time responsiveness, and a polynomial regression algorithm is used for correction to establish a more complex data relationship model and improve correction accuracy. For high-risk situations, a Kalman filter algorithm is used for data fusion and correction. The state estimate is dynamically updated through the Kalman filter to provide more accurate correction results, and correction is combined with redundant sensor data. Multi-sensor data cross-validation is used to improve the accuracy of correction.

[0055] After executing the correction strategy, the compensated displacement data is marked, the parameters and methods in the compensation process are recorded to ensure the traceability of the data, and the compensation marking result is generated. The displacement monitoring result is generated based on the compensation marking result. Specifically, the compensated displacement data is integrated with other sensor data, such as pressure, temperature, and vibration, to form the displacement monitoring result.

[0056] Furthermore, the method provided in the application embodiment also includes:

[0057] The displacement sensor is calibrated and analyzed to establish a calibration zero point; an adaptive attenuation compensation function of the displacement sensor is established with the calibration zero point as an evaluation starting point; and adaptive compensation of real-time displacement results is performed using the adaptive attenuation compensation function.

[0058] In the embodiment of the present application, the displacement sensor is first placed on a standard device with a known displacement value, and the zero point and range of the sensor are automatically adjusted by the internal calibration module so that its output is consistent with the standard displacement. A high-precision reference displacement device, such as a laser interferometer, is used to ensure the accuracy of the calibration. The zero point value of the sensor is determined through multiple automatic measurements and averaging.

[0059] Next, the adaptive attenuation compensation function of the displacement sensor is established with the calibration zero point as the evaluation starting point. The adaptive attenuation compensation function is used to correct the mathematical model of the sensor measurement error. Specifically, the displacement data and actual displacement value of the sensor are automatically collected under different environmental conditions and operating conditions, and the data is continuously monitored and recorded through the data acquisition system. After that, the collected data is compared with the actual displacement value, and the error characteristics of the sensor output are automatically analyzed using the built-in statistical analysis tool to determine the law of error changes over time and environment. Using the error analysis results, the adaptive attenuation compensation function is established using methods such as linear regression or polynomial regression.

[0060] Finally, adaptive compensation of real-time displacement results is performed through adaptive attenuation compensation function. Specifically, adaptive compensation refers to dynamically applying compensation function to correct sensor output in the actual measurement process to improve measurement accuracy. During the operation of the cylinder, the displacement data output by the sensor is monitored in real time. According to the current environmental conditions and operating status, the real-time displacement data is input into the adaptive attenuation compensation function, the compensation value is calculated, and the compensation value is applied to the sensor output to obtain the corrected displacement data.

[0061] Furthermore, the method provided in the application embodiment also includes:

[0062] Based on the displacement monitoring result, a fault prediction result of the oil cylinder is established, and a prediction verification node is generated; prediction verification is performed at the prediction verification node, and a health management plan is constructed based on the prediction verification result; and compensation management of the oil cylinder is performed through the health management plan.

[0063] In an embodiment of the present application, first, a fault prediction result of the oil cylinder is established based on the displacement monitoring result. Using historical data and current monitoring results, possible fault modes and abnormal behaviors are identified through statistical analysis and time series analysis methods. Specifically, displacement data is collected in real time and stored in a database. Then, historical data is processed using statistical analysis tools to identify long-term trends and cyclical changes. Next, the ARIMA model is used for time series prediction. The steps of constructing the ARIMA model include determining the model parameters p (autoregressive order) and q (moving average order) using autocorrelation functions and partial autocorrelation function graphs. The model parameters are estimated using the maximum likelihood estimation method. The white noise characteristics of the residual are checked to ensure that the model fits well. Finally, the constructed ARIMA model is used to predict future data points and identify possible future failure time points.

[0064] Next, the prediction verification node is generated based on the fault prediction results. The prediction verification node refers to the critical moment for detailed inspection and verification of the oil cylinder under specific time or conditions. According to the time series analysis results, the high-risk time period is identified, and the setting of the verification node is optimized in combination with historical fault data and operating environment to ensure its rationality and effectiveness.

[0065] At the prediction verification node, prediction verification is performed. Prediction verification is the actual verification of the cylinder's operating status and prediction results at the predetermined verification node. Specific steps include using sensors and data acquisition systems to monitor the cylinder's operating parameters, such as displacement, pressure, and temperature, in real time. By comparing actual data and prediction results, the prediction model is adjusted using residual analysis methods to improve prediction accuracy. Based on the prediction verification results, a health management plan is constructed. The health management plan is a set of maintenance, servicing, and troubleshooting plans based on the cylinder's actual operating status and prediction results. Use data analysis tools to analyze the prediction verification results to identify potential problems and risks. Based on the analysis results, a health management plan is formulated using a rule-based expert system, including regular maintenance plans, emergency treatment measures, and spare parts management strategies. Rule-based expert systems apply pre-set rules to simulate the decision-making process of human experts.

[0066] Finally, the oil cylinder compensation management is carried out through the health management plan.

[0067] Furthermore, the method provided in the application embodiment also includes:

[0068] A displacement warning is established according to the real-time control parameters, wherein the displacement warning includes a substantial displacement warning and a risk displacement warning. A joint warning identification is performed on the displacement monitoring result through the substantial displacement warning and the risk displacement warning, and the joint warning identification result is reported.

[0069] In the embodiment of the present application, firstly, a displacement warning is established according to the real-time control parameters. The displacement warning includes a substantial displacement warning and a risk displacement warning.

[0070] The actual displacement warning is based on the displacement data directly measured by the sensor. When the monitored displacement data exceeds the preset safety threshold, the actual displacement warning is triggered. Specifically, a high-precision displacement sensor, such as a laser displacement sensor and a data acquisition system, is used to monitor the displacement data of the oil cylinder in real time and transmit it to the central processing unit; the safety threshold of the displacement data is set by technical experts based on the design specifications and operating experience of the oil cylinder; when the monitored displacement data exceeds the preset threshold, the actual displacement warning is triggered.

[0071] Risk displacement warning is a warning based on the comprehensive analysis of multiple real-time control parameters. By using statistical analysis and data fusion technology, the changing trends of displacement, pressure, temperature and other parameters are analyzed to predict possible risks. Specifically, through sensor networks (including pressure sensors, temperature sensors, etc.) and data acquisition systems, such as SCADA systems, multiple control parameters such as displacement, pressure, temperature, etc. are collected in real time; data fusion technology (such as Kalman filtering) and statistical analysis tools are used for data fusion to analyze the correlation and changing trends between various parameters; trend analysis, such as linear regression, moving average and association rule mining technology, such as Apriori algorithm, is used to predict possible risks. When the risk indicator reaches the preset threshold, the risk displacement warning is triggered.

[0072] Next, the displacement monitoring results are jointly identified through the actual displacement warning and risk displacement warning. Joint warning identification refers to the comprehensive judgment of the operating status of the oil cylinder by combining the results of the actual displacement warning and the risk displacement warning. Specifically, the results of the actual displacement warning and the risk displacement warning are integrated through a data fusion algorithm (such as the weighted average method) to form comprehensive warning data; the comprehensive warning data is analyzed using a logistic regression algorithm to identify potential faults and anomalies. The specific steps include extracting key features from the warning data, such as the real-time values ​​of displacement, pressure, and temperature and their rates of change; using standardization methods such as Z-score standardization to standardize the feature data to eliminate dimensional differences; using historical fault data to train the logistic regression model and determine the model parameters through the maximum likelihood estimation method; using the cross-validation method to evaluate the performance of the model to ensure that the model has good generalization ability; inputting the comprehensive warning data collected in real time into the trained logistic regression model, calculating the probability of fault occurrence, and judging whether to trigger the joint warning based on the preset threshold.

[0073] According to the joint identification results, the probability value output by the logistic regression model is used to divide the warning into low risk, medium risk and high risk for subsequent processing. Finally, the joint warning identification results are reported. Specifically, according to the joint warning identification results, the report generation tool is used to generate warning information, including warning type, warning level, related parameters, etc.; the warning information is sent to relevant personnel and management systems through the warning system, such as the SCADA system.

[0074] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:

[0075] The present application starts the central processing unit of the joint displacement sensing system, performs a self-test of the joint sensor group, and if the self-test result is a passing result, performs a reference zero point correction on the joint sensor group; activates the displacement sensor of the joint sensor group, performs displacement data recording of the cylinder piston, and establishes a real-time displacement result; activates the pressure sensor, temperature sensor, and vibration sensor of the linkage sensor, performs linkage data collection through the pressure sensor, temperature sensor, and vibration sensor, and establishes an additional data set; obtains the real-time control parameters of the cylinder, performs parameter analysis on the real-time control parameters, inputs the parameter analysis results and the additional data set into the joint authentication network, performs joint authentication of the cylinder working status, and establishes an authentication influence coefficient; inputs the additional data set and the real-time displacement result into the displacement background correction network, performs displacement correction of the real-time displacement result, and generates a displacement correction result; establishes an authentication risk based on the authentication influence coefficient, performs a displacement correction result compensation mark based on the authentication risk, and generates a displacement monitoring result based on the compensation mark result. The present invention solves the technical problem of insufficient accuracy of the hydraulic cylinder displacement sensing method in the prior art, by starting a central processing unit, performing self-checking and zero-point correction, activating sensors to record data, establishing additional data sets, parsing control parameters and performing state authentication, inputting a correction network to generate correction results, establishing authentication risks and compensation identification, and finally generating displacement monitoring results, thereby achieving the technical effect of improving the cylinder displacement measurement accuracy.

[0076] Embodiment 2, based on the same inventive concept as the combined displacement sensing method for the oil cylinder in the above embodiment, Figure 2 As shown, the present application provides a combined displacement sensing platform for a cylinder, and the platform and method embodiments in the present application are based on the same inventive concept. The platform includes:

[0077] A sensor self-check module 11, wherein the sensor self-check module 11 starts the central processing unit of the joint displacement sensor system, performs a self-check of the joint sensor group, and if the self-check result is a passing result, the joint sensor group is subjected to a reference zero point correction; a displacement data recording module 12, wherein the displacement data recording module 12 activates the displacement sensor of the joint sensor group, performs displacement data recording of the cylinder piston, and establishes a real-time displacement result; a linkage data acquisition module 13, wherein the linkage data acquisition module 13 activates the pressure sensor, temperature sensor, and vibration sensor of the linkage sensor, performs linkage data acquisition through the pressure sensor, temperature sensor, and vibration sensor, and establishes an additional data set; a joint authentication module Block 14, the joint authentication module 14 obtains the real-time control parameters of the cylinder, performs parameter analysis on the real-time control parameters, inputs the parameter analysis results and the additional data set into the joint authentication network, performs joint authentication of the cylinder working status, and establishes an authentication influence coefficient; the displacement correction module 15, the displacement correction module 15 inputs the additional data set and the real-time displacement result into the displacement background correction network, performs displacement correction of the real-time displacement result, and generates a displacement correction result; the compensation identification module 16, the compensation identification module 16 establishes an authentication risk based on the authentication influence coefficient, performs a compensation identification on the displacement correction result based on the authentication risk, and generates a displacement monitoring result based on the compensation identification result.

[0078] Furthermore, the platform is also used to implement the following functions:

[0079] The data of the cylinder is collected through the data collection unit to establish a historical working data set; a digital twin model of the cylinder is established according to the historical working data set and the attribute information of the cylinder, and a control parameter working condition simulation is performed based on the digital twin model, and the model parameters of the digital twin model are updated according to the simulation results; the parameter analysis results are synchronized to the digital twin model of the updated model parameters, and the real-time simulation results of the digital twin model are fed back to the joint authentication network; and the joint authentication network is used to perform a joint authentication of the cylinder working status based on the real-time simulation results and the additional data set.

[0080] Furthermore, the platform is also used to implement the following functions:

[0081] The continuous working time of the oil cylinder is obtained, and a pre-response window is established based on the continuous working time; the pre-working data is called through the pre-response window, an impact evaluation of the pre-working state is performed, and a pre-working state impact evaluation result is established; and the digital twin model is initialized and managed according to the pre-working state impact evaluation result.

[0082] Furthermore, the platform is also used to implement the following functions:

[0083] S1: configuring a timing attenuation factor based on the preceding response window; S2: performing a load analysis on the preceding work data to establish a timing load evaluation result; S3: performing load compensation on the timing load evaluation result according to the timing attenuation factor to establish a first preceding work state impact evaluation result; S4: performing a load fluctuation evaluation on the preceding work data to establish a second preceding work state impact evaluation result based on the load fluctuation evaluation result and the timing attenuation factor; S5: establishing a preceding work state impact evaluation result based on the first preceding work state impact evaluation result and the second preceding work state impact evaluation result.

[0084] Furthermore, the platform is also used to implement the following functions:

[0085] The displacement sensor is calibrated and analyzed to establish a calibration zero point; an adaptive attenuation compensation function of the displacement sensor is established with the calibration zero point as an evaluation starting point; and adaptive compensation of real-time displacement results is performed using the adaptive attenuation compensation function.

[0086] Furthermore, the platform is also used to implement the following functions:

[0087] Based on the displacement monitoring result, a fault prediction result of the oil cylinder is established, and a prediction verification node is generated; prediction verification is performed at the prediction verification node, and a health management plan is constructed based on the prediction verification result; and compensation management of the oil cylinder is performed through the health management plan.

[0088] Furthermore, the platform is also used to implement the following functions:

[0089] A displacement warning is established according to the real-time control parameters, wherein the displacement warning includes a substantial displacement warning and a risk displacement warning. A joint warning identification is performed on the displacement monitoring result through the substantial displacement warning and the risk displacement warning, and the joint warning identification result is reported.

[0090] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0091] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0092] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. Combined displacement sensing method for oil cylinders, It is characterized in that The method comprises: Starting the central processing unit of the joint displacement sensor system to perform a self-check of the joint sensor group, and if the self-check result is a passing result, performing a reference zero point calibration on the joint sensor group; Activate the displacement sensor of the joint sensor group, perform displacement data recording of the cylinder piston, and establish real-time displacement results; Activate the pressure sensor, temperature sensor, and vibration sensor of the linkage sensor, perform linkage data collection through the pressure sensor, temperature sensor, and vibration sensor, and establish an additional data set; Acquire the real-time control parameters of the oil cylinder, perform parameter analysis on the real-time control parameters, input the parameter analysis results and additional data sets into the joint authentication network, perform joint authentication of the oil cylinder working status, and establish an authentication influence coefficient; Inputting the additional data set and the real-time displacement result into a displacement background correction network, performing displacement correction on the real-time displacement result, and generating a displacement correction result; Establishing an authentication risk based on the authentication influence coefficient, performing a compensation mark on a displacement correction result based on the authentication risk, and generating a displacement monitoring result based on the compensation mark result; The step of acquiring the real-time control parameters of the oil cylinder, performing parameter analysis on the real-time control parameters, inputting the parameter analysis results and the additional data set into the joint authentication network, and performing the joint authentication of the working status of the oil cylinder further includes: Collect data from the oil cylinder through the data acquisition unit and establish a historical working data set; Establishing a digital twin model of the oil cylinder according to the historical working data set and the attribute information of the oil cylinder, performing control parameter working condition simulation based on the digital twin model, and updating model parameters of the digital twin model according to the simulation results; Synchronizing the parameter analysis results into the digital twin model of the updated model parameters, and feeding back the real-time simulation results of the digital twin model to the joint authentication network; The joint certification network is used to perform joint certification of the cylinder working status based on the real-time simulation results and the additional data set.

2. The combined displacement sensing method for a cylinder as claimed in claim 1, It is characterized in that The step of synchronizing the parameter analysis results to the digital twin model of the updated model parameters and feeding back the real-time simulation results of the digital twin model to the joint authentication network also includes: Acquire the continuous working time of the oil cylinder, and establish a pre-response window based on the continuous working time; Calling the preceding work data through the preceding response window, conducting an impact evaluation of the preceding work status, and establishing a preceding work status impact evaluation result; The digital twin model is initialized and managed according to the previous working state impact evaluation result.

3. The combined displacement sensing method for a cylinder as claimed in claim 2, It is characterized in that The calling of the preceding work data through the preceding response window to evaluate the impact of the preceding work status and establishing the preceding work status impact evaluation result also includes: S1: configuring a timing attenuation factor based on the preceding response window; S2: Perform load analysis on the pre-work data to establish a time series load evaluation result; S3: performing load compensation on the time series load evaluation result according to the time series attenuation factor to establish a first pre-working state impact evaluation result; S4: performing load fluctuation evaluation on the pre-operation data, and establishing a second pre-operation state impact evaluation result based on the load fluctuation evaluation result and the time series attenuation factor; S5: Establishing a pre-working state impact evaluation result based on the first pre-working state impact evaluation result and the second pre-working state impact evaluation result.

4. The combined displacement sensing method for a cylinder as claimed in claim 1, It is characterized in that The method further comprises: Performing calibration analysis on the displacement sensor to establish a calibration zero point; Taking the zero point adjustment as the evaluation starting point, the adaptive attenuation compensation function of the displacement sensor is established; The adaptive attenuation compensation function is used to adaptively compensate the real-time displacement result.

5. The combined displacement sensing method for a cylinder as claimed in claim 1, It is characterized in that The method further comprises: Establishing a fault prediction result of the oil cylinder based on the displacement monitoring result, and generating a prediction verification node; Perform prediction verification at the prediction verification node, and build a health management plan based on the prediction verification result; Compensation management of the oil cylinder is performed through the health management solution.

6. The combined displacement sensing method for a cylinder as claimed in claim 1, It is characterized in that The method further comprises: Establishing a displacement warning according to the real-time control parameters, wherein the displacement warning includes a substantial displacement warning and a risk displacement warning; The displacement monitoring result is subjected to joint early warning identification through the substantial displacement early warning and risk displacement early warning, and the joint early warning identification result is reported.

7. Combined displacement sensing platform for oil cylinders, It is characterized in that Used to perform the combined displacement sensing method for a cylinder according to any one of claims 1 to 6, the platform comprising: A sensor self-check module, wherein the sensor self-check module starts the central processing unit of the joint displacement sensor system, performs a self-check of the joint sensor group, and performs a reference zero point calibration on the joint sensor group if the self-check result is a passing result; A displacement data recording module, wherein the displacement data recording module activates the displacement sensor of the joint sensor group, performs displacement data recording of the oil cylinder piston, and establishes a real-time displacement result; A linkage data acquisition module, wherein the linkage data acquisition module activates a pressure sensor, a temperature sensor, and a vibration sensor of the linkage sensor, performs linkage data acquisition through the pressure sensor, the temperature sensor, and the vibration sensor, and establishes an additional data set; A joint authentication module, wherein the joint authentication module obtains real-time control parameters of the oil cylinder, performs parameter analysis on the real-time control parameters, inputs the parameter analysis results and additional data sets into a joint authentication network, performs joint authentication of the working status of the oil cylinder, and establishes an authentication influence coefficient; A displacement correction module, wherein the displacement correction module inputs the additional data set and the real-time displacement result into a displacement background correction network, performs displacement correction on the real-time displacement result, and generates a displacement correction result; A compensation identification module is provided, wherein the compensation identification module establishes an authentication risk based on the authentication influence coefficient, performs a compensation identification on a displacement correction result based on the authentication risk, and generates a displacement monitoring result based on the compensation identification result.

Images