Intelligent monitoring management method and system for electronic control system of petroleum drilling machine VFD room

Abstract

The invention discloses a petroleum drilling machine VFD room electric control system intelligent monitoring management method and system. The intelligent monitoring management method comprises the steps that a VFD room electric control system database is established; performing noise reduction preprocessing on the historical data and the real-time monitoring data; establishing a VFD room electric control system feature database; performing fault diagnosis on the acquired real-time monitoring data based on a VFD room electric control system feature database; and performing fault prediction on the VFD room electric control system. Through transformation from traditional digital electric control to intelligent control and recording of historical data and operation curves of key electrical parameters and faults of the equipment, a supporting basis can be provided for the fault state and preventive maintenance of the equipment, and the intelligent management level of an electric control system on a drilling site is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of drilling monitoring, and particularly relates to an intelligent monitoring and management method and system for the electric control system of the VFD room of an oil drilling rig. Background Art

[0002] As the electric control system of the variable frequency drive (VFD) room, which is the core power control source in the oil drilling industry, it is the power distribution and control center for all the electrical equipment at the drilling site and plays a very important role. However, currently, the main electric control systems of oil drilling equipment mostly adopt an electric control mode with industrial frequency converters of manufacturers such as Siemens as the core and a PLC programmable logic controller for the logic control of the entire system. Due to the characteristics of the oil drilling industry, this mode has been used in the electric control system part for many years and continues to this day without corresponding technical improvements and system upgrades. The intelligent monitoring technology has not been effectively integrated into the existing oil drilling electric control system, bringing many inconveniences to the use of on-site engineers. Specifically, it is difficult to directly diagnose faults online in the existing oil drilling monitoring system, and it is difficult to locate and predict faults. As a result, sometimes faults cannot be discovered in time, delaying production; it does not have the function of saving historical data, lacks the curve records of key electrical parameters, and cannot analyze the usage status of equipment, providing no reasonable basis for equipment pre-maintenance. Summary of the Invention

[0003] In view of the above problems, the present invention discloses an intelligent monitoring and management method for the electric control system of the VFD room of an oil drilling rig, including:

[0004] Establishing a database for the electric control system of the VFD room;

[0005] Performing noise reduction preprocessing on historical data and real-time monitoring data;

[0006] Establishing a feature database for the electric control system of the VFD room;

[0007] Based on the feature database of the electric control system of the VFD room, performing fault diagnosis on the collected real-time monitoring data;

[0008] Performing fault prediction on the electric control system of the VFD room.

[0009] Furthermore, before establishing the database for the electric control system of the VFD room, the following steps are also included:

[0010] Constructing the software layer of the intelligent monitoring and management system for the electric control system of the VFD room of an oil drilling rig;

[0011] Building the control layer of the intelligent monitoring and management system for the electric control system of the VFD room of an oil drilling rig.

[0012] Further, the historical data or real-time monitoring data includes the operation, maintenance, test, and historical fault data of the VFD room electrical control system.

[0013] Further, the specific steps for establishing the characteristic database of the VFD room electrical control system are as follows:

[0014] According to the preprocessed historical data and real-time monitoring data, extract the relationship between characteristic parameters and faults as the fault criterion, and establish a data model for the VFD room electrical equipment.

[0015] Based on the data model of the VFD room electrical equipment, monitor, diagnose, and predict the operating status of the VFD room electrical equipment. Through continuous learning and improvement, obtain the characteristic database of the VFD room electrical control system.

[0016] Further, the specific steps for fault diagnosis of the real-time monitoring data collected based on the characteristic database of the VFD room electrical control system are as follows:

[0017] Based on the characteristic database of the VFD room electrical control system, compare the real-time monitoring data with the fault criterion to determine whether the equipment has entered a fault state.

[0018] Further, the specific steps for fault prediction of the VFD room electrical control system are as follows:

[0019] Construct the memory gate, forget gate, and output gate network structures of the LSTM neural network, and initialize the parameters of the LSTM neural network.

[0020] Substitute the preprocessed training set data into the LSTM neural network for training to obtain the corresponding parameters.

[0021] Use the test set data to perform simulation tests on the trained LSTM neural network and adjust the set parameters.

[0022] Calculate the generalization error and training error of the LSTM neural network prediction results to obtain a model performance evaluation.

[0023] Based on the LSTM neural network, perform fault prediction on the VFD room electrical control system.

[0024] Further, before constructing the memory gate, forget gate, and output gate network structures of the LSTM neural network and initializing the parameters of the LSTM neural network, the following steps are included:

[0025] Randomly divide the preprocessed data set into a training set and a test set according to the ratio of n1:n2 based on the sample size.

[0026] Further, the parameters include the gate weight coefficient and the bias coefficient.

[0027] The present invention also discloses an intelligent monitoring and management system for the electric control system of the VFD house of an oil drilling rig based on the above-mentioned intelligent monitoring and management method for the electric control system of the VFD house of an oil drilling rig, including: a software layer, a control layer, and an equipment layer;

[0028] The software layer is connected to the control layer;

[0029] The control layer is connected to the equipment layer;

[0030] The software layer includes a data acquisition subsystem, a data processing subsystem, a data storage subsystem, a fault diagnosis and monitoring subsystem, and an intelligent human-machine interaction subsystem.

[0031] Furthermore, the control layer includes a local server, a data acquisition IO station, a switch, a first wireless network, and a second wireless network;

[0032] The data acquisition IO station is connected to the local server through the switch;

[0033] The local server is connected to the software layer;

[0034] The first wireless network is connected to the local server;

[0035] The first wireless network is connected to the second wireless network;

[0036] The equipment layer includes the electrical equipment in the VFD house and a PLC;

[0037] The data acquisition IO station is respectively connected to the electrical equipment in the VFD house and the PLC.

[0038] Compared with the prior art, the embodiments of the present invention have at least the following advantages: The present invention aims at the problems of difficult fault diagnosis and prediction in the monitoring system of the electric control system of the VFD house of an oil drilling rig, establishes a database for the electric control system of the VFD house based on MySQL (My Structured Query Language), records and stores the operation data of the electric control system of the VFD house, and provides data support for system fault diagnosis and prediction; by performing noise reduction preprocessing on a large amount of read operation data, the safety and effectiveness of the data are ensured, thereby improving the accuracy of fault diagnosis and prediction; the Monte Carlo probability statistics method is adopted to extract the correlation characterization between feature parameters and fault characteristics, establish a data model for the electrical equipment in the VFD house, and realize fault diagnosis; at the same time, an intelligent algorithm based on a neural network model is adopted to predict the system fault; it enables the traditional digital electric control to transform into intelligence, and the recording of the historical data and operation curves of the key electrical parameters and faults of the equipment can provide a support basis for the fault state and preventive maintenance of the equipment, and improve the intelligent management level of the electric control system at the drilling site.

[0039] Other features and advantages of the present invention will be set forth in the following description, and in part will be obvious from the description, or may be learned by practice of the present invention. The objectives and other advantages of the present invention may be realized and attained by the structure particularly pointed out in the specification and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0041] Figure 1 Shows a flowchart of an intelligent monitoring and management method for the electric control system of an oil rig VFD house according to an embodiment of the present invention;

[0042] Figure 2 Shows a schematic structural diagram of an intelligent monitoring and management system for the electric control system of an oil rig VFD house according to an embodiment of the present invention;

[0043] Figure 3 Shows a schematic diagram of the hardware connection of an intelligent monitoring and management system for the electric control system of an oil rig VFD house according to an embodiment of the present invention.

[0044] Reference numerals: 1, data acquisition subsystem; 2, data processing subsystem; 3, data storage subsystem; 4, fault diagnosis and monitoring subsystem; 5, intelligent human-computer interaction subsystem; 6, local server; 7, data acquisition IO station; 8, switch; 9, first wireless network; 10, electrical equipment in the VFD house; 11, PLC; 12, industrial control computer; 13, web server; 14, network router; 15, Internet; 16, captain's room; 17, second wireless network. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following clearly and completely describes the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0046] How to combine the characteristics of the oil drilling industry, utilize the "Internet of Things" to establish a remote monitoring platform, collect information on the usage of equipment and conduct big data analysis, build an intelligent supervision platform for the VFD room electrical control system, preprocess the system operation data to ensure data accuracy and thereby improve the system's fault prediction accuracy, and at the same time provide a fault diagnosis method based on intelligent algorithms for the system, so as to reduce the fault downtime, has become extremely urgent.

[0047] Figure 1 The flowchart of the intelligent monitoring and management method for the VFD room electrical control system of an oil drilling rig according to an embodiment of the present invention is shown. As Figure 1 shown, an intelligent monitoring and management method for the VFD room electrical control system of an oil drilling rig proposed by the present invention includes the following steps:

[0048] Step 1: Construct the software layer of the intelligent monitoring and management system for the VFD room electrical control system of the oil drilling rig;

[0049] The software layer of an intelligent monitoring and management system for the VFD room electrical control system of an oil drilling rig includes a data acquisition subsystem 1, a data processing subsystem 2, a data storage subsystem 3, a fault diagnosis and monitoring subsystem 4, and an intelligent human-computer interaction subsystem 5.

[0050] Step 2: Build the control layer (hardware platform) of the intelligent monitoring and management system for the VFD room electrical control system of the oil drilling rig;

[0051] As Figure 3 shown, the input end of the data acquisition IO station 7 is connected to the VFD room electrical equipment 10 and the PLC 11, and the output end is connected to the local server 6 of the remote monitoring and management system. The output end of the local server 6 is connected to the team leader's room 16 through the switch 8 and to the Internet 15 through the network router 14, and wireless access is also supported. Among them, the VFD room electrical equipment 10 includes a braking resistor, a main transformer, an inverter, etc.

[0052] Details are as Figure 3 shown. The intelligent monitoring and management system hardware platform is in the dotted box and includes a local server 6, a data acquisition IO station 7, a switch 8, a first wireless network 9, a second wireless network 17, etc.

[0053] 1) Sensor data acquisition IO station 7

[0054] Establish a VFD room industrial control computer 12 and a data acquisition IO station 7. The input of the data acquisition IO station 7 is the communication of the drilling rig PLC and the basic sensor data, and the output end is connected to the local server 6 through the switch 8. The data acquisition IO station 7 is integrated into an indoor electrical control box and installed in the VFD room PLC cabinet. The data acquisition IO station 7 is deployed near the equipment position to be collected considering on-site practicality and sensor types.

[0055] 2) Local server 6

[0056] The local server 6 is used to receive and store on-site data, establish a corresponding database, and the local data client is used to display the on-site data. The local server 6 is connected to the Internet 15 via the network router 14 to achieve device interconnection.

[0057] 3) Wellsite local area network

[0058] Fully considering the on-site working conditions and the environment where the drilling rig is located, install an industrial outdoor wireless communication access point in the VFD room to establish a local dedicated WIFI communication network for the intelligent monitoring and management system of the drilling rig equipment, meeting the industrial wireless network communication within a range of 300 meters on-site. The on-site WIFI network encrypts data transmission using the WPA2-PSK Enterprise method and uses a hierarchical authorization password method to prevent illegal network access.

[0059] Step 3: Establish a database for the VFD room electrical control system;

[0060] Establish a database for the VFD room electrical control system based on MySQL (My Structured Query Language) according to historical data and real-time monitoring data.

[0061] Step 4: Data preprocessing;

[0062] Perform noise reduction preprocessing on historical data and online real-time monitoring data. Use the clustering analysis method based on k-means to perform rule-based outlier screening, valid data filling, and correction of data with obvious faults on the sampled data, reducing the training error of the model, avoiding overfitting phenomena, realizing data screening and preprocessing, and improving the accuracy of fault diagnosis and prediction. The specific steps are as follows:

[0063] Step 4.1: Initialize k sample points as clustering center points a = a1, a2,..., a k . a k is the kth clustering center point.

[0064] Step 4.2: Calculate the distance from each data sample x m in the data set (i.e., the historical data and real-time monitoring data after noise reduction preprocessing) to the k initial clustering center points and compare them, and divide it into the nearest clustering center point. x m is the mth data sample.

[0065] Step 4.3: For each category c j , j = 1, 2,..., k, recalculate the coordinate mean of the objects in each category and use it as the new clustering center

[0066] Step 4.4: Recalculate the distance of each data sample x m to the new cluster center and reclassify it to the cluster center that is closest to itself.

[0067] Step 4.5: Repeat Steps 4.3 and 4.4 until the condition threshold is reached. Here, the condition threshold refers to whether the distance between the new cluster center and the old cluster center reaches a value range. After reaching the value range, the classification is completed. Exemplarily, the condition threshold is 0, that is, the new cluster center and the old cluster center completely coincide.

[0068] Step 5: Establish a feature database for the VFD room electrical control system;

[0069] Step 5.1: According to the operation, maintenance, test, and historical fault data of the VFD room electrical control system after preprocessing (the preprocessed historical data and real-time monitoring data), use the Monte Carlo probability statistics method to extract the relationship between the feature parameters and the faults (correlation characterization), and set thresholds for the feature parameters corresponding to the faults as the fault criteria to establish a data model for the VFD room electrical equipment; when a fault occurs, the corresponding feature parameters such as voltage signals, current signals, or temperatures are different from the normal values, and the data during the fault is characterized corresponding to the fault. Exemplarily, the faults include motor open-phase faults, inverter undervoltage faults, ground faults, etc.

[0070] Step 5.2: Based on the data model of the VFD room electrical equipment, through monitoring, diagnosing, and predicting the operating status of the VFD room electrical equipment 10, continuously learning and improving during this process, gradually correcting and perfecting, to obtain the feature database of the VFD room electrical control system.

[0071] Step 6: Based on the feature database of the VFD room electrical control system, perform fault diagnosis on the collected real-time monitoring data;

[0072] Based on the feature database of the VFD room electrical control system, according to the real-time monitoring data sampled by the data acquisition subsystem (the data acquisition IO station 7 sends the collected real-time monitoring data to the data acquisition subsystem 1 through the industrial control computer 12), by comparing with the fault criteria, if the fault criteria are met, it indicates that the equipment has entered the fault state, and alarm and fault display are performed; if the fault criteria are not met, normal equipment monitoring is performed.

[0073] Step 7: Fault prediction;

[0074] The fault diagnosis and monitoring subsystem 4 incorporates a fault prediction algorithm based on the Long Short-Term Memory (LSTM) neural network to predict faults. LSTM is a special type of recurrent neural network (RNN) that alleviates problems such as gradient vanishing and gradient explosion by adding input gates, output gates, and forget gates, thereby improving the accuracy of fault prediction.

[0075] The preprocessed dataset is randomly divided into a training set and a test set in the ratio of n1:n2 according to the sample size. Here, n1 refers to the proportion of the training set, and n2 refers to the proportion of the test set.

[0076] Use the training set and the test set to build a model for the LSTM neural network. The detailed steps are as follows:

[0077] Step 7.1: Construct the memory gate, forget gate, and output gate network structures of the LSTM neural network, and initialize parameters such as the gate weight coefficients and bias coefficients of the LSTM neural network;

[0078] Memory gate:

[0079] i t =σ(W ix x t +W ih h t-1 +b i ) (1)

[0080] iC t =tanh(W cx x t +W ch h t-1 +b c ) (2)

[0081] Where, i t is the output of the sigmoid neural network layer, W ix is the weight coefficient of x t in the sigmoid neural network layer, x t is the data input at the current time t, W ih is the weight coefficient of h t-1 in the sigmoid neural network layer, h t-1 is the data output module of the previous time, b i is the bias coefficient of the sigmoid neural network layer, iC t is the output of the memory gate, W cx is the weight coefficient of x t in the tanh neural network layer, W chFor the weight coefficient h in the tanh neural network layer t-1 and b c is the bias coefficient of the tanh neural network layer, σ is the sigmoid neural network layer, and tanh is the tanh neural network layer.

[0082] It can be seen from the above formula that the memory gate includes a sigmoid neural network layer and a tanh neural network layer.

[0083] Forget gate:

[0084] f t = σ(W fx x t + W fh h t-1 + b f ) (3)

[0085] where f t is the output of the forget gate; W fx is the weight coefficient of x t in the forget gate; W fh is the weight coefficient of h t-1 in the forget gate; b f is the bias coefficient of the forget gate.

[0086] Output gate:

[0087] C t = i t × iC t + f t × C t-1 (4)

[0088] where C t is the memory module at the current moment. That is, multiply the output f t of the forget gate by the memory module C t-1 at the previous moment, multiply the output iC t of the memory gate by i t , and sum the two parts to obtain the new memory module C t .

[0089] Neuron module output:

[0090] o t = σ(W ox x t + W oh h t-1 + b o ) (5)

[0091] h t = o t × tanh(Ct ) (6)

[0092] where o t is the output of the neuron module; W ox is the weight coefficient of x t in the neuron module; W oh is the weight coefficient of h t-1 in the neuron module; b o is the bias coefficient of the neuron module; h t is the data output module at time t.

[0093] Step 7.2: Substitute the training set data obtained after preprocessing into the LSTM neural network model for training to obtain corresponding parameters;

[0094] Step 7.3: Use the test set data to perform simulation tests on the trained LSTM neural network model and adjust the set parameters;

[0095] Step 7.4: Calculate the generalization error and training error of the model prediction results to obtain the model performance evaluation.

[0096] Based on the LSTM neural network, perform fault prediction on the VFD room electric control system.

[0097] Step 8: Build an intelligent human-computer interaction subsystem of an intelligent monitoring and management system based on the client-server mode (B / S). The human-computer interface uses a navigation bar + tab page method for switching.

[0098] In view of the problems of difficult fault diagnosis and prediction existing in the monitoring system of the VFD room electric control system of the oil drilling rig, the present invention establishes a VFD room electric control system database based on MySQL (My Structured Query Language) to record and store the operation data of the VFD room electric control system, providing data support for system fault diagnosis and prediction; through noise reduction preprocessing of a large amount of read operation data, ensuring the safety and effectiveness of the data, thereby improving the accuracy of fault diagnosis and prediction; adopting the method of Monte Carlo probability statistics to extract the correlation characterization between feature parameters and fault characteristics, establishing a data model of VFD room electrical equipment to achieve fault diagnosis; at the same time, using an intelligent algorithm based on a neural network model to predict system faults; transforming traditional digital electric control into intelligence, and recording the key electrical parameters and historical data and operation curves of faults of the equipment, which can provide a support basis for the fault status and preventive maintenance of the equipment, and improve the intelligent management level of the electric control system at the drilling site.

[0099] Such as Figure 2As shown in the figure, based on the above intelligent monitoring and management method for the electric control system of the VFD room of an oil drilling rig, the present invention proposes an intelligent monitoring and management system for the electric control system of the VFD room of an oil drilling rig, including: a software layer, a control layer, and an equipment layer;

[0100] The software layer is connected to the control layer;

[0101] The control layer is connected to the equipment layer;

[0102] The software layer includes a data acquisition subsystem 1, a data processing subsystem 2, a data storage subsystem 3, a fault diagnosis and monitoring subsystem 4, and an intelligent human-computer interaction subsystem 5.

[0103] The data acquisition subsystem 1 is used to acquire on-site data;

[0104] The data processing subsystem 2 is used to process the acquired data;

[0105] The data storage subsystem 3 is used to store the acquired data;

[0106] The fault diagnosis and monitoring subsystem 4 is used for fault diagnosis and monitoring;

[0107] The intelligent human-computer interaction subsystem 5 is used for human-computer interaction.

[0108] In some embodiments, the control layer includes a local server 6, a data acquisition IO station 7, a switch 8, a first wireless network 9, and a second wireless network 17;

[0109] The data acquisition IO station 7 is connected to the local server 6 through the switch 8;

[0110] The local server 6 is connected to the software layer;

[0111] The local server 6 includes an industrial control computer 12 and a web server 13;

[0112] The industrial control computer 12 is connected to the web server 13;

[0113] The data acquisition IO station 7 is connected to the industrial control computer 12 through the switch 8, and the industrial control computer 12 is respectively connected to the data acquisition subsystem 1, the data processing subsystem 2, the data storage subsystem 3, the fault diagnosis and monitoring subsystem 4, and the intelligent human-computer interaction subsystem 5;

[0114] The first wireless network 9 is connected to the local server 6;

[0115] The first wireless network 9 is connected to the second wireless network 17; the second wireless network 17 is connected to the team leader's room 16;

[0116] The equipment layer includes the electrical equipment 10 in the VFD room and the PLC 11; among them, the PLC 11 is also connected to the PC side for displaying the data of the electric control system;

[0117] The data acquisition I / O station 7 is respectively connected to the electrical equipment 10 in the VFD room and the PLC 11.

[0118] The local server 6 is used to provide network services;

[0119] The data acquisition I / O station 7 is used to collect data;

[0120] The switch 8 is used for data packet transfer;

[0121] The first wireless network 9 is used to transmit signals;

[0122] The second wireless network 17 is used to receive signals;

[0123] The PLC 11 is used for data acquisition, control and underlying data communication;

[0124] The industrial control computer 12 is used to run the operating system.

[0125] The local server 6 and the captain's room 16 can communicate either wired or wirelessly.

[0126] The intelligent monitoring and management system for the electric control system of the VFD room of the oil drilling rig adopts the B / S architecture to achieve high-speed data acquisition and network sharing. At the drilling site, the high-performance industrial control computer 12 is used to collect the on-site equipment information, engineering parameters, and work report data and store and manage them uniformly in the local server 6 deployed on-site. The data of multiple well sites are collected in the data center through cloud services, and intelligent algorithms are used to analyze the real-time and historical data to guide production operations.

[0127] In the intelligent monitoring and management system for the electric control system of the VFD room of the oil drilling rig of the present invention, the data acquisition subsystem 1 measures the environmental physical quantities of the VFD room and the parameters of the electrical equipment 10 in the VFD room through digital measurement technology to generate the original database. After data screening, intelligent algorithms are used to train the data samples, extract fault features, and establish the corresponding feature database. The fault diagnosis and monitoring subsystem 4 can quickly diagnose and predict faults using intelligent algorithms. The diagnosis results are displayed and alarmed in real time through the intelligent human-computer interaction subsystem 5, enabling the system to quickly locate faults and make predictions, providing valuable information for equipment maintenance, minimizing the failure rate, and increasing the service life of the equipment; it can achieve in-depth management of the electric control system that meets the requirements of centralized monitoring, accident prevention, and rapid maintenance.

[0128] The intelligent monitoring and management system of the electric control system for the VFD house of the oil drilling rig according to the present invention can, on the one hand, save the operation data of electrical equipment, solve the problem that the traditional monitoring system cannot read historical data, thereby providing a basis for analyzing the usage status of the equipment and at the same time providing data support for intelligent fault diagnosis and prediction methods; on the other hand, the intelligent fault prediction and diagnosis method based on data preprocessing proposed by the present invention can solve the problem that the current traditional monitoring system cannot accurately locate and predict faults, thereby reducing the fault downtime and improving the operation and maintenance efficiency.

[0129] Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. Intelligent monitoring and management method for the electric control system of the VFD room of an oil drilling rig, characterized in that, Including: Establish a database for the electrical control system of the VFD room; Perform noise reduction preprocessing on historical data and real-time monitoring data; Establish a feature database for the electrical control system of the VFD room; Based on the feature database of the electrical control system of the VFD room, perform fault diagnosis on the collected real-time monitoring data; Perform fault prediction on the electrical control system of the VFD room.

2. The intelligent monitoring and management method for the electric control system of the VFD house of an oil drilling rig according to claim 1, characterized in that, Before establishing the database for the electrical control system of the VFD room, the following steps are also included: Construct the software layer of the intelligent monitoring and management system for the electrical control system of the VFD room of the oil drilling rig; Build the control layer of the intelligent monitoring and management system for the electrical control system of the VFD room of the oil drilling rig.

3. The intelligent monitoring and management method for the electric control system of the VFD house of an oil drilling rig according to claim 1, characterized in that, The historical data or real-time monitoring data includes the operation, maintenance, test, and historical fault data of the electrical control system of the VFD room.

4. The intelligent monitoring and management method for the electric control system of the oil drilling rig VFD house according to claim 1 or 3, characterized in that, The specific steps for establishing the feature database of the electrical control system of the VFD room are as follows: According to the preprocessed historical data and real-time monitoring data, extract the relationship between feature parameters and faults as fault criteria, and establish a data model for the electrical equipment in the VFD room; Based on the data model of the electrical equipment in the VFD room, monitor, diagnose, and predict the operating status of the electrical equipment (10) in the VFD room. Through continuous learning and improvement, obtain the feature database of the electrical control system of the VFD room.

5. The intelligent monitoring and management method for the electric control system of the VFD house of an oil drilling rig according to claim 1, characterized in that The specific steps for performing fault diagnosis on the collected real-time monitoring data based on the feature database of the electrical control system of the VFD room are as follows: Based on the feature database of the electrical control system of the VFD room, compare the real-time monitoring data with the fault criteria to determine whether the equipment has entered a fault state.

6. The intelligent monitoring and management method for the electric control system of the VFD house of an oil drilling rig according to claim 1, characterized in that, The specific steps for performing fault prediction on the electrical control system of the VFD room are as follows: Construct the memory gate, forget gate, and output gate network structures of the LSTM neural network, and initialize the parameters of the LSTM neural network; Substitute the preprocessed training set data into the LSTM neural network for training to obtain the corresponding parameters; Use the test set data to perform simulation tests on the trained LSTM neural network and adjust the set parameters; Calculate the generalization error and training error of the prediction results of the LSTM neural network to obtain a model performance evaluation; Based on the LSTM neural network, perform fault prediction on the electrical control system of the VFD room.

7. The intelligent monitoring and management method for the electric control system of the VFD house of an oil drilling rig according to claim 6, characterized in that, Before constructing the memory gate, forget gate, and output gate network structures of the LSTM neural network and initializing the parameters of the LSTM neural network, the following steps are included: Randomly divide the preprocessed data set into a training set and a test set according to the ratio of n1:n2 based on the sample size.

8. The intelligent monitoring and management method for the electric control system of the VFD house of an oil drilling rig according to claim 6, characterized in that, The parameters include gate weight coefficients and bias coefficients.

9. An intelligent monitoring and management system for the electric control system of the VFD house of an oil drilling rig, which is based on the intelligent monitoring and management method for the electric control system of the VFD house of an oil drilling rig according to any one of claims 1-8, characterized in that, Including: Software layer, control layer, and device layer; The software layer is connected to the control layer; The control layer is connected to the device layer; The software layer includes a data acquisition subsystem (1), a data processing subsystem (2), a data storage subsystem (3), a fault diagnosis and monitoring subsystem (4), and an intelligent human-computer interaction subsystem (5).

10. The intelligent monitoring and management system for the electric control system of the VFD house of an oil drilling rig according to claim 9, characterized in that, The control layer includes a local server (6), a data acquisition IO station (7), a switch (8), a first wireless network (9), and a second wireless network (17); The data acquisition IO station (7) is connected to the local server (6) through the switch (8); The local server (6) is connected to the software layer; The first wireless network (9) is connected to the local server (6); The first wireless network (9) is connected to the second wireless network (17); The device layer includes VFD room electrical equipment (10) and a PLC (11); The data acquisition I / O station (7) is respectively connected to the VFD room electrical equipment (10) and the PLC (11).

Images