A data acquisition method and system for a variable frequency drive system for oil drilling rigs

By constructing a key parameter prediction model and adaptive control method in the variable frequency drive system of oil drilling rigs, and dynamically adjusting the data acquisition frequency, the problems of resource waste and insufficient data capture in the existing technology are solved, and efficient response for resource optimization and fault detection is achieved.

CN119434940BActive Publication Date: 2026-11-17SICHUAN HONGHUA ELECTRIC
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411503010.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-10-25
Publication Date
2026-11-17
Estimated Expiration
2044-10-25

AI Technical Summary

Technical Problem

The existing data acquisition methods of oil drilling rig variable frequency drive systems use a fixed acquisition frequency, which cannot be dynamically adjusted according to working conditions. This leads to wasted resources and insufficient capture of key data, affecting the effectiveness of monitoring and fault detection.

Method used

A key parameter prediction model and adaptive control method are used to dynamically adjust the data acquisition frequency. A frequency adjustment mechanism is constructed by using an ARIMA prediction model and autocorrelation function, and the frequency can be flexibly adjusted by combining it with an adaptive control module.

Benefits of technology

It improved resource utilization efficiency, enhanced the system's ability to respond to emergencies, ensured the accurate capture of key data and timely early warning of faults, and optimized data processing efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119434940B_ABST
    Figure CN119434940B_ABST
Patent Text Reader

Abstract

This invention discloses a data acquisition method and system for a variable frequency drive system of an oil drilling rig. The method includes the following steps: acquiring key parameter data of the oil drilling rig variable frequency drive system according to an initial data acquisition frequency; training a key parameter prediction model and using the trained model to obtain predicted key parameter data; dynamically adjusting the data acquisition frequency using an adaptive control method and using the dynamically adjusted frequency to acquire key parameter data of the oil drilling rig variable frequency drive system; and encapsulating and storing the key parameter data. This invention achieves resource optimization and flexible response to changes in operating conditions by dynamically adjusting the acquisition frequency. Under stable operating conditions, the frequency is reduced to save resources, while under abnormal operating conditions, the frequency is increased to ensure accurate capture of key data. This not only improves resource utilization efficiency but also enhances the system's responsiveness to emergencies.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of data acquisition for variable frequency drive systems in oil drilling rigs, and specifically to a data acquisition method and system for variable frequency drive systems in oil drilling rigs. Background Technology

[0002] In oil drilling operations, variable frequency drive (VFD) systems are widely used to control the electric motors of drilling rigs, ensuring their efficient and stable operation under various complex conditions. To ensure the performance and safety of the VFD system, real-time monitoring and data acquisition of its key operating parameters are necessary. These parameters include, but are not limited to, voltage, current, speed, torque, vibration, and temperature. High-frequency data acquisition provides crucial information for system optimization, fault diagnosis, and preventative maintenance.

[0003] The existing data acquisition methods for oil drilling rig variable frequency drive systems have the following main drawbacks:

[0004] (1) Fixed acquisition frequency. Existing methods typically use a fixed acquisition frequency, which cannot be dynamically adjusted according to the operating conditions of the variable frequency drive system. This fixed frequency leads to unnecessary waste of resources, such as storage space and processor resources, when the drilling rig load is stable. When the operating conditions of the variable frequency drive system change drastically, the fixed low-frequency acquisition cannot capture critical high-frequency data, missing important abnormal information. Ultimately, this method limits the response capability of the variable frequency drive system to sudden situations and affects the effectiveness of monitoring and fault detection;

[0005] (2) Insufficient flexibility in data acquisition. Existing methods lack flexibility and struggle to adjust the acquisition frequency based on changes in operating conditions or sensor type. Operating requirements vary significantly across different operational phases, but existing methods cannot intelligently adjust the data acquisition strategy for each channel. Some key parameters require higher acquisition frequencies, but existing methods cannot effectively address these needs, resulting in low resource utilization and impacting the effectiveness and accuracy of data acquisition. Summary of the Invention

[0006] To address the aforementioned shortcomings in the prior art, this invention provides a data acquisition method and system for a variable frequency drive system for oil drilling rigs.

[0007] To achieve the above-mentioned objectives, the technical solution adopted by this invention is as follows:

[0008] A data acquisition method for a variable frequency drive system of an oil drilling rig includes the following steps:

[0009] S1. Initialize the data acquisition frequency and acquire key parameter data of the oil drilling rig frequency converter drive system according to the initial data acquisition frequency.

[0010] S2. Construct a key parameter prediction model. Use the key parameter data of the oil drilling rig variable frequency drive system in step S1 to train the key parameter prediction model, and use the trained key parameter prediction model to obtain key parameter prediction data.

[0011] S3. Based on the key parameter prediction data in step S2, the data acquisition frequency is dynamically adjusted using the adaptive control method, and the key parameter data of the oil drilling rig frequency converter drive system is acquired using the dynamically adjusted data acquisition frequency.

[0012] S4. Encapsulate the key parameter data of the oil drilling rig variable frequency drive system in step S3 and store it in the database.

[0013] Further, in step S1, the key parameter data of the oil drilling rig variable frequency drive system are constructed into input sample data, represented as follows:

[0014]

[0015] Where: X is the input sample, x11 is the first key parameter at the first observation time, x12 is the second key parameter at the first observation time, and x1 n x21 is the nth key parameter at the first observation time, x22 is the first key parameter at the second observation time, and x23 is the second key parameter at the second observation time. n xn1 is the first key parameter at the second observation time, xn2 is the second key parameter at the nth observation time, and xn is the third key parameter at the second observation time. n This is the nth key parameter at the nth observation time.

[0016] Further, in step S2, a key parameter prediction model is constructed, including the following steps:

[0017] A1. Construct ARIMA prediction models for all key parameters respectively;

[0018] A2. Construct a matrix by treating each ARIMA prediction model from step A1 as an element to obtain the key parameter prediction model, as follows:

[0019]

[0020] Where: ξ is the key parameter prediction model, ξ1 is the ARIMA prediction model for the first key parameter, ξ2 is the ARIMA prediction model for the second key parameter, and ξ... n The ARIMA prediction model for the nth key parameter.

[0021] Further, in step A1, the ARIMA prediction model includes a time series model and a non-stationary time series model. The time series model is represented as follows:

[0022]

[0023] Where: y t Here are the predicted values ​​of the key parameters at time t, where c is a constant term. y is the first autoregressive coefficient. t-1 For the predicted values ​​of key parameters at time t-1, The second autoregressive coefficient, y t-2 For the predicted values ​​of key parameters at time t-2, Let y be the p-th autoregressive coefficient, where p is the first model parameter. t-p Here are the predicted values ​​of the key parameters at time tp, θ1 is the first moving average coefficient, and z... t-1 Let z be white noise at time t-1, θ2 be the second moving average coefficient, and z be the white noise at time t-1. t-2 For white noise at time t-2, θ q z is the coefficient of the q-th moving average, q is the second model parameter, and z t-q For white noise at time tq, z t White noise at time t;

[0024] The non-stationary time series model is represented as:

[0025]

[0026] Where: Δ d This is the difference operator of degree d, where d is the degree of difference.

[0027] Furthermore, the key parameter prediction model is trained using the key parameter data of the oil drilling rig variable frequency drive system in step S1, and the key parameter prediction data is obtained using the trained key parameter prediction model, including the following steps:

[0028] B1. Select the degree of difference, and use the autocorrelation function and partial correlation function to determine the parameters of the first model and the second model;

[0029] B2. Based on the difference order, first model parameters and second model parameters in step B1, the key parameter prediction model is trained using the key parameter data of the oil drilling rig variable frequency drive system in step S1. The autoregressive coefficients and moving average coefficients in the model are determined, and the optimal autoregressive coefficients and moving average coefficients are determined by the maximum likelihood estimation method to obtain the trained key parameter prediction model.

[0030] B3. Determine the set future prediction points and use the trained key parameter prediction model to obtain key parameter prediction data.

[0031] Furthermore, in step S3, based on the key parameter prediction data in step S2, the data acquisition frequency is dynamically adjusted using an adaptive control method. The specific process is as follows: based on the key parameter prediction data in step S2, the rate of change of the predicted value is calculated; it is determined whether the rate of change of the predicted value continuously exceeds the rate of change threshold within a set time step length; if so, the data acquisition frequency is increased using an adaptive control method; otherwise, the data acquisition frequency is decreased using an adaptive control method.

[0032] Furthermore, by using adaptive control to increase the data acquisition frequency, it can be expressed as:

[0033] f new =min(f max ,f now +Δf),

[0034]

[0035] Where: f new This represents the adjusted data acquisition frequency, where min indicates the minimum value, and f is the value of the minimum. max f is the maximum data acquisition frequency. now Let y be the current data acquisition frequency, Δf be the dynamic increment of the data acquisition frequency, λ be the adjustment coefficient, and y be the variable frequency. t For the predicted value of the key parameter y at time t t-1 Predicted values ​​for key parameters at time t-1;

[0036] Reducing the data acquisition frequency using adaptive control is expressed as:

[0037] f new =max(f min ,f now -Δf)

[0038] Where: max represents the maximum value sign, f min This is the minimum data acquisition frequency.

[0039] A data acquisition system for a variable frequency drive system of an oil drilling rig using the above method includes a data reading module, a sliding window analysis module, an adaptive control module, and a data storage module.

[0040] The data reading module is used to initialize the data acquisition frequency and acquire key parameter data of the oil drilling rig frequency converter drive system according to the initial data acquisition frequency;

[0041] The sliding window analysis module is used to build a key parameter prediction model. It trains the key parameter prediction model using key parameter data of the oil drilling rig variable frequency drive system, and uses the trained key parameter prediction model to obtain key parameter prediction data.

[0042] The adaptive control module is used to predict data based on key parameters, dynamically adjust the data acquisition frequency using the adaptive control method, and acquire key parameter data of the oil drilling rig frequency converter drive system using the dynamically adjusted data acquisition frequency.

[0043] The data storage module is used to encapsulate the key parameter data of the oil drilling rig's variable frequency drive system and store it in the database.

[0044] The present invention has the following beneficial effects:

[0045] (1) This invention dynamically adjusts the data acquisition frequency by using key parameter prediction data and adaptive control method, and uses the dynamically adjusted data acquisition frequency to acquire key parameter data of the oil drilling rig frequency converter drive system. Specifically, the frequency is reduced to save resources under stable working conditions, while the frequency is increased to ensure accurate acquisition of key data under abnormal working conditions. This achieves resource optimization and flexible response to changes in working conditions, which not only improves resource utilization efficiency, but also enhances the system's ability to respond to emergencies.

[0046] (2) By dynamically adjusting the acquisition frequency, this invention can ensure that the high-frequency changes of the oil drilling rig frequency converter drive system can be quickly captured under critical operating conditions, effectively improving the accuracy and integrity of data acquisition, and ensuring accurate monitoring of the system's operating status and timely early warning of potential faults.

[0047] (3) By dynamically adjusting the acquisition frequency, the present invention reduces unnecessary data volume and lowers the system’s demand for storage and transmission resources. This not only optimizes the efficiency of subsequent data processing, but also provides a guarantee for long-term stable operation and subsequent data analysis.

[0048] (4) This invention provides a data acquisition system for a variable frequency drive system of an oil drilling rig, including a data reading module, a sliding window analysis module, an adaptive control module, and a data storage module; the data reading module can be used to initialize the data acquisition frequency and acquire key parameter data of the variable frequency drive system of the oil drilling rig according to the initial data acquisition frequency; the sliding window analysis module can be used to construct a key parameter prediction model, train the key parameter prediction model using the key parameter data of the variable frequency drive system of the oil drilling rig, and obtain key parameter prediction data using the trained key parameter prediction model; the adaptive control module can be used to dynamically adjust the data acquisition frequency using an adaptive control method according to the key parameter prediction data, and acquire key parameter data of the variable frequency drive system of the oil drilling rig using the dynamically adjusted data acquisition frequency; the data storage module can be used to encapsulate the key parameter data of the variable frequency drive system of the oil drilling rig and store it in a database. Attached Figure Description

[0049] Figure 1A schematic diagram of a data acquisition method for a variable frequency drive system of an oil drilling rig;

[0050] Figure 2 This is a schematic diagram of the data acquisition system structure of a variable frequency drive system for an oil drilling rig. Detailed Implementation

[0051] The specific embodiments of the present invention are described below to enable those skilled in the art to understand the present invention. However, it should be understood that the present invention is not limited to the scope of the specific embodiments. For those skilled in the art, various changes are obvious as long as they are within the spirit and scope of the present invention as defined and determined by the appended claims. All inventions utilizing the concept of the present invention are protected.

[0052] like Figure 1 As shown, a data acquisition method for an oil drilling rig variable frequency drive system includes steps S1-S4, as detailed below:

[0053] S1. Initialize the data acquisition frequency and acquire key parameter data of the oil drilling rig frequency converter drive system according to the initial data acquisition frequency.

[0054] In an optional embodiment of the present invention, after collecting key parameter data of the oil drilling rig variable frequency drive system, the present invention constructs the key parameter data of the oil drilling rig variable frequency drive system into input sample data, represented as follows:

[0055]

[0056] Where: X is the input sample, x11 is the first key parameter at the first observation time, x12 is the second key parameter at the first observation time, and x1 n x21 is the nth key parameter at the first observation time, x22 is the first key parameter at the second observation time, and x23 is the second key parameter at the second observation time. n xn1 is the first key parameter at the second observation time, xn2 is the second key parameter at the nth observation time, and xn is the third key parameter at the second observation time. n This is the nth key parameter at the nth observation time.

[0057] The key parameters of the variable frequency drive system for oil drilling rigs in this invention include, but are not limited to, voltage, current, torque, speed, vibration, and temperature.

[0058] S2. Construct a key parameter prediction model. Use the key parameter data of the oil drilling rig variable frequency drive system in step S1 to train the key parameter prediction model, and use the trained key parameter prediction model to obtain key parameter prediction data.

[0059] In an optional embodiment of the present invention, the present invention constructs a key parameter prediction model, including the following steps:

[0060] A1. Construct ARIMA prediction models for all key parameters separately.

[0061] ARIMA prediction models include time series models and non-stationary time series models. The time series model is represented as follows:

[0062]

[0063] Where: y t Here are the predicted values ​​of the key parameters at time t, where c is a constant term. y is the first autoregressive coefficient. t-1 For the predicted values ​​of key parameters at time t-1, The second autoregressive coefficient, y t-2 For the predicted values ​​of key parameters at time t-2, Let y be the p-th autoregressive coefficient, where p is the first model parameter. t-p Here are the predicted values ​​of the key parameters at time tp, θ1 is the first moving average coefficient, and z... t-1 Let z be white noise at time t-1, θ2 be the second moving average coefficient, and z be the white noise at time t-1. t-2 For white noise at time t-2, θ q z is the coefficient of the q-th moving average, q is the second model parameter, and z t-q For white noise at time tq, z t Let be white noise at time t.

[0064] The non-stationary time series model is represented as:

[0065]

[0066] Where: Δ d This is the difference operator of degree d, where d is the degree of difference.

[0067] A2. Construct a matrix by treating each ARIMA prediction model from step A1 as an element to obtain the key parameter prediction model, as follows:

[0068]

[0069] Where: ξ is the key parameter prediction model, ξ1 is the ARIMA prediction model for the first key parameter, ξ2 is the ARIMA prediction model for the second key parameter, and ξ... n The ARIMA prediction model for the nth key parameter.

[0070] This invention utilizes the key parameter data of the oil drilling rig variable frequency drive system in step S1 to train a key parameter prediction model, and uses the trained key parameter prediction model to obtain key parameter prediction data, including the following steps:

[0071] B1. Select the degree of difference and use the autocorrelation function and partial correlation function to determine the first model parameters and the second model parameters.

[0072] This invention uses autocorrelation function and partial correlation function to determine the first model parameters and the second model parameters. The specific process is as follows:

[0073] The autocorrelation function of the key parameter sequence calculated in this invention is expressed as:

[0074]

[0075] Where: p(k) is the autocorrelation coefficient with lag order k, t is time, T is the sample size, and y t For the predicted values ​​of key parameters at time t, y is the mean of the predicted values ​​of the key parameters within the sample. t-k Predicted values ​​for key parameters at time tk;

[0076] The partial correlation function of the key parameter sequence calculated in this invention is expressed as:

[0077]

[0078] in: Let be the partial autocorrelation coefficient with lag order k, and p(ki) be the autocorrelation coefficient with lag order ki. It is the partial autocorrelation coefficient with lag order i, used to calculate the partial autocorrelation coefficient with lag order k.

[0079] This invention dynamically adjusts the first and second model parameters based on the analysis results of the autocorrelation function and partial autocorrelation function of the aforementioned key parameter sequences. When the autocorrelation and partial autocorrelation are significant (i.e., the calculated results exceed a set threshold), the first and second model parameters are adjusted to obtain the optimal adjusted result, thereby determining the first and second model parameters.

[0080] B2. Based on the difference order, first model parameters and second model parameters in step B1, the key parameter prediction model is trained using the key parameter data of the oil drilling rig variable frequency drive system in step S1. The autoregressive coefficients and moving average coefficients in the model are determined, and the optimal autoregressive coefficients and moving average coefficients are determined by the maximum likelihood estimation method to obtain the trained key parameter prediction model.

[0081] B3. Determine the set future prediction points and use the trained key parameter prediction model to obtain key parameter prediction data.

[0082] Specifically, after obtaining key parameter prediction data using the trained key parameter prediction model, this invention calculates the prediction error of the trained key parameter prediction model using the root mean square method, as follows:

[0083]

[0084] Where: MSE is the prediction error of the key parameter prediction model, N is the total number of samples in the prediction data, i is the index of the prediction data, and y i For the predicted value of the i-th key parameter, This represents the mean of the predicted values ​​of key parameters within the total sample of the predicted data.

[0085] This invention monitors whether the prediction error is within an acceptable range; if the prediction error continues to be high, it indicates that the current first model parameters and second model parameters are not suitable for the current working conditions and need to be dynamically adjusted; otherwise, no adjustment is made.

[0086] S3. Based on the key parameter prediction data in step S2, the data acquisition frequency is dynamically adjusted using the adaptive control method, and the key parameter data of the oil drilling rig frequency converter drive system is acquired using the dynamically adjusted data acquisition frequency.

[0087] In an optional embodiment of the present invention, the present invention dynamically adjusts the data acquisition frequency based on the key parameter prediction data in step S2 using an adaptive control method. The specific process is as follows: based on the key parameter prediction data in step S2, calculate the rate of change of the predicted value; determine whether the rate of change of the predicted value continuously exceeds the rate of change threshold within a set time step length; if so, increase the data acquisition frequency using an adaptive control method; otherwise, decrease the data acquisition frequency using an adaptive control method.

[0088] This invention calculates the rate of change of predicted values, expressed as:

[0089]

[0090] Where: σ is the rate of change of the predicted value in the interval from time t-1 to time t, y t For the predicted value of the key parameter y at time t t-1 These are the predicted values ​​for key parameters at time t-1.

[0091] This invention utilizes an adaptive control method to increase the data acquisition frequency, as expressed as:

[0092] f new =min(f max ,f now +Δf),

[0093]

[0094] Where: f new This represents the adjusted data acquisition frequency, where min indicates the minimum value, and f is the value of the minimum. max f is the maximum data acquisition frequency. now Let y be the current data acquisition frequency, Δf be the dynamic increment of the data acquisition frequency, λ be the adjustment coefficient, and y be the variable frequency. t For the predicted value of the key parameter y at time t t-1 Predicted values ​​for key parameters at time t-1;

[0095] This invention utilizes an adaptive control method to reduce the data acquisition frequency, as expressed as:

[0096] f new =max(f min ,f now -Δf)

[0097] Where: max represents the maximum value sign, f min This is the minimum data acquisition frequency.

[0098] S4. Encapsulate the key parameter data of the oil drilling rig variable frequency drive system in step S3 and store it in the database.

[0099] In an optional embodiment of the present invention, a data storage module is constructed to encapsulate key parameter data of the oil drilling rig variable frequency drive system and store it in a database.

[0100] like Figure 2 As shown, a data acquisition system for an oil drilling rig variable frequency drive system using the above method includes a data reading module, a sliding window analysis module, an adaptive control module, and a data storage module.

[0101] In an optional embodiment of the present invention, the data reading module is connected to the sensors of each device. The data reading module is used to initialize the data acquisition frequency and collect data from the sensors of each device according to the initial data acquisition frequency in order to collect key parameter data of the oil drilling rig frequency converter drive system.

[0102] In an optional embodiment of the present invention, the sliding window analysis module is used to construct a key parameter prediction model, train the key parameter prediction model using key parameter data of the oil drilling rig variable frequency drive system, and obtain key parameter prediction data using the trained key parameter prediction model.

[0103] In an optional embodiment of the present invention, the adaptive control module is used to predict data based on key parameters, dynamically adjust the data acquisition frequency using an adaptive control method, and acquire key parameter data of the oil drilling rig frequency converter drive system using the dynamically adjusted data acquisition frequency.

[0104] In an optional embodiment of the present invention, the data storage module is used to encapsulate key parameter data of the oil drilling rig variable frequency drive system and store it in a database.

[0105] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0106] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0107] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0108] Specific embodiments have been used to illustrate the principles and implementation methods of this invention. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.

[0109] Those skilled in the art will recognize that the embodiments described herein are intended to help the reader understand the principles of the invention, and should be understood that the scope of protection of the invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific modifications and combinations based on the technical teachings disclosed in this invention without departing from the spirit of the invention, and these modifications and combinations are still within the scope of protection of this invention.

Claims

1. A data acquisition method for a variable frequency drive system of an oil drilling rig, characterized in that, Includes the following steps: S1. Initialize the data acquisition frequency and acquire key parameter data of the oil drilling rig frequency converter drive system according to the initial data acquisition frequency. S2. Construct a key parameter prediction model. Use the key parameter data of the oil drilling rig variable frequency drive system in step S1 to train the key parameter prediction model, and use the trained key parameter prediction model to obtain key parameter prediction data. S3. Based on the key parameter prediction data in step S2, the data acquisition frequency is dynamically adjusted using the adaptive control method, and the key parameter data of the oil drilling rig frequency converter drive system is acquired using the dynamically adjusted data acquisition frequency. S4. Encapsulate the key parameter data of the oil drilling rig frequency converter drive system in step S3 and store it in the database; In step S1, the key parameter data of the oil drilling rig variable frequency drive system are constructed into input sample data, represented as follows: in: For the input sample, The first key parameter at the first observation time. The second key parameter at the first observation time. For the nth key parameter at the first observation time, This is the first key parameter for the second observation time. This is the second key parameter at the second observation time. For the nth key parameter at the second observation time, The first key parameter at the nth observation time. The second key parameter at the nth observation time. This is the nth key parameter at the nth observation time; In step S2, a key parameter prediction model is constructed, including the following steps: A1. Construct ARIMA prediction models for all key parameters respectively; A2. Construct a matrix by treating each ARIMA prediction model from step A1 as an element to obtain the key parameter prediction model, as follows: in: For key parameter prediction models, ARIMA prediction model with the first key parameter The ARIMA prediction model for the second key parameter. For the ARIMA prediction model of the nth key parameter; In step A1, the ARIMA prediction model includes a time series model and a non-stationary time series model. The time series model is represented as follows: in: In time Predicted values ​​of key parameters For constant terms, The first autoregressive coefficient, In time Predicted value of key parameter -1 The second autoregressive coefficient, In time Predicted values ​​of key parameters for -2, For the first Autoregressive coefficient, These are the parameters of the first model. In time - Predicted values ​​of key parameters The first moving average coefficient, In time -1 white noise, The second moving average coefficient, In time -2 white noise For the first Moving average coefficient For the second model parameters, In time - White noise, In time White noise; The non-stationary time series model is represented as: in: for Secondary difference operator. The degree of the difference; The key parameter prediction model is trained using the key parameter data of the oil drilling rig variable frequency drive system in step S1, and the key parameter prediction data is obtained using the trained key parameter prediction model, including the following steps: B1. Select the difference order, and use the autocorrelation function and partial correlation function to determine the parameters of the first model and the second model; B2. Based on the difference order, first model parameters and second model parameters in step B1, the key parameter prediction model is trained using the key parameter data of the oil drilling rig variable frequency drive system in step S1. The autoregressive coefficients and moving average coefficients in the model are determined, and the optimal autoregressive coefficients and moving average coefficients are determined by the maximum likelihood estimation method to obtain the trained key parameter prediction model. B3. Determine the set future prediction points and use the trained key parameter prediction model to obtain key parameter prediction data; In step S3, based on the key parameter prediction data in step S2, the data acquisition frequency is dynamically adjusted using an adaptive control method. The specific process is as follows: based on the key parameter prediction data in step S2, the rate of change of the predicted value is calculated; it is determined whether the rate of change of the predicted value continuously exceeds the rate of change threshold within a set time step length; if so, the data acquisition frequency is increased using an adaptive control method; otherwise, the data acquisition frequency is decreased using an adaptive control method. Increasing the data acquisition frequency using adaptive control is expressed as: , in: The adjusted data acquisition frequency, To take the sign of the minimum value, To the maximum data acquisition frequency, The current data collection frequency, This represents the dynamic increment of the data acquisition frequency. For adjustment coefficients, In time Predicted values ​​of key parameters In time Predicted values ​​of key parameters -1; Reducing the data acquisition frequency using adaptive control is expressed as: in: To take the sign of the maximum value, This is the minimum data acquisition frequency.

2. A data acquisition system for an oil drilling rig variable frequency drive system using the method described in claim 1, characterized in that, It includes a data reading module, a sliding window analysis module, an adaptive control module, and a data storage module; The data reading module is used to initialize the data acquisition frequency and acquire key parameter data of the oil drilling rig frequency converter drive system according to the initial data acquisition frequency; The sliding window analysis module is used to build a key parameter prediction model. It uses the key parameter data of the oil drilling rig variable frequency drive system to train the key parameter prediction model, and uses the trained key parameter prediction model to obtain key parameter prediction data. The adaptive control module is used to predict data based on key parameters, dynamically adjust the data acquisition frequency using adaptive control, and acquire key parameter data of the oil drilling rig frequency converter drive system using the dynamically adjusted data acquisition frequency. The data storage module is used to encapsulate the key parameter data of the oil drilling rig's variable frequency drive system and store it in the database.

Citation Information

Patent Citations

  • Collection method for wireless sensor network data based on time series prediction model

    CN101511099A

  • AI and IOT internet-of-things-based interconnection synchronization shopping mall and supermarket management method and platform

    CN118710223A