Oilfield equipment operation state intelligent analysis and fault early warning system

Abstract

The invention belongs to the field of oil field equipment management, and discloses an oil field equipment operation state intelligent analysis and fault early warning system which comprises a clustering control module and a plurality of wireless sensor nodes. The clustering control module is used for dividing the distribution range of all the wireless sensor nodes into a plurality of local ranges according to a clustering rule, respectively acquiring member nodes and cluster head nodes in each local range, generating a clustering result and sending the clustering result to each wireless sensor node; the wireless sensor nodes obtain own role types and clusters to which the wireless sensor nodes belong according to clustering results; the role type is a non-cluster head node or a cluster head node; the non-cluster-head nodes are used for acquiring monitoring parameters of the oil field equipment and transmitting the monitoring parameters to the cluster-head nodes of the clusters where the non-cluster-head nodes are located. According to the invention, the number of local ranges can be more effectively controlled, excessive number of local ranges is avoided, the forwarding times of the monitoring parameters are inhibited, and the transmission efficiency of the monitoring parameters is better improved.

Description

Technical Field

[0001] The present invention relates to the field of oilfield equipment management, and in particular to an intelligent analysis and fault early warning system for oilfield equipment operation status. Background Art

[0002] By monitoring the status of oilfield equipment through sensors, it is possible to issue early warnings in time when the status of oilfield equipment is abnormal, thereby effectively maintaining the safe operation of oilfield equipment and ensuring the normal exploitation of oil. In the prior art, sensor networks are usually used to collect data from oilfield equipment, and the ability of nodes in the sensor network to communicate with each other is used to monitor equipment in large areas of oilfields. However, this monitoring method still has certain defects. This method generally directly divides the distribution range of oilfield equipment into a fixed number of local ranges, and then clusters each local range separately. This clustering method does not take into account the impact of the number of local ranges on transmission efficiency, which easily leads to an excessive number of local ranges. The more local ranges there are, the more times the status parameters of the oilfield equipment are forwarded during transmission to the host computer, making it impossible to obtain the status parameters of the oilfield equipment in a timely manner. Summary of the invention

[0003] The purpose of the present invention is to disclose an intelligent analysis and fault warning system for the operation status of oilfield equipment to solve the technical problems raised in the background technology.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] The present invention provides an intelligent analysis and fault warning system for oilfield equipment operation status, including a clustering control module and a plurality of wireless sensor nodes;

[0006] The clustering control module is used to divide the distribution range of all wireless sensor nodes into multiple local ranges according to the clustering rules, and to obtain the member nodes and cluster head nodes in each local range respectively, generate clustering results, and send the clustering results to each wireless sensor node;

[0007] The wireless sensor node obtains its own role type and the cluster to which it belongs according to the clustering result; the role type is non-cluster head node or cluster head node; the non-cluster head node is used to obtain the monitoring parameters of the oilfield equipment and transmit them to the cluster head node of the cluster where it is located;

[0008] Among them, the distribution range of all wireless sensor nodes is divided into multiple local ranges according to the clustering rule, including:

[0009] Create a control function:

[0010]

[0011] F(n) represents the control function, n represents the number of local ranges, area i represents the area of ​​the ith local range, area represents the area of ​​the distribution range of all wireless sensor nodes, and dist i represents the average distance between the cluster head node and other cluster head nodes in the i-th local range; the value range of n is [1, N], N represents the total number of wireless sensor nodes; dma represents the maximum distance between any two wireless sensor nodes; α represents the weight;

[0012] The value of n that makes the control function reach the maximum value is expressed as M;

[0013] The distribution range of all wireless sensor nodes is divided into M local ranges.

[0014] Preferably, it also includes a data transmission and communication module;

[0015] The cluster head node is used to obtain the monitoring parameters of the oilfield equipment and to transmit the monitoring parameters to the data transmission and communication module.

[0016] Preferably, transmitting the monitoring parameters to the data transmission and communication module comprises:

[0017] The cluster head node transmits the acquired monitoring parameters of the oil field equipment and the monitoring parameters received from the non-cluster head nodes to the data transmission and communication module.

[0018] Preferably, it also includes a data storage module;

[0019] The data transmission and communication module is used to transmit the received monitoring parameters to the data storage module;

[0020] The data storage module is used to store monitoring parameters.

[0021] Preferably, it also includes a data preprocessing module;

[0022] The data preprocessing module is used to filter the monitoring parameters newly stored in the data storage module to obtain the filtered monitoring parameters.

[0023] Preferably, it also includes a fault diagnosis module;

[0024] The fault diagnosis module is used to perform intelligent analysis on the filtered monitoring parameters and obtain the diagnosis results of the oilfield equipment.

[0025] Preferably, it also includes an early warning module;

[0026] The early warning module is used to send an alarm message to the operation and maintenance personnel when the diagnosis result shows an abnormality.

[0027] Preferably, the area of ​​the local range is determined in the following manner:

[0028] Establish a rectangular coordinate system for the distribution range of all wireless sensor nodes;

[0029] Obtain the maximum value x2 of the X-axis coordinate, the minimum value x1 of the X-axis coordinate, the maximum value y2 of the Y-axis coordinate, and the minimum value y1 of the Y-axis coordinate of the distribution range of all wireless sensor nodes in the rectangular coordinate system;

[0030] Let D represent the area to be segmented; for any point in D with coordinates (x, y), the value range of x is [x1, x2] and the value range of y is [y1, y2];

[0031] The length of the local range is Width is

[0032] Preferably, dist i The acquisition process includes:

[0033] According to the clustering rules, the cluster head nodes in each local range are obtained respectively;

[0034] The average distance dist between the cluster head node and other cluster head nodes in the i-th local range i The calculation formula is:

[0035]

[0036] dto i,j represents the distance between the cluster head node in the ith local range and the jth cluster head node in the set DT, where DT is the set of all cluster head nodes except the cluster head node in the ith local range.

[0037] Preferably, according to the clustering rule, the cluster head nodes in each local range are obtained respectively, including:

[0038] Calculate the transmission quality value of each wireless sensor node in each local range respectively;

[0039] The wireless sensor node with the largest transmission quality value is regarded as the cluster head node in the local range, and the remaining wireless sensor nodes are regarded as non-cluster head nodes in the local range.

[0040] Beneficial effects:

[0041] In the process of using the sensor network to monitor the operating status of oilfield equipment and to warn of faults, the present invention does not use a fixed number of local ranges, but establishes a control function and uses the value of n that makes the control function obtain the maximum value as the number of local ranges finally determined. In this way, the number of local ranges can be changed with the change of clustering rules and the state of the wireless sensor node, and the number of local ranges can be more effectively controlled to avoid an excessive number of local ranges, suppress the forwarding times of monitoring parameters, better improve the transmission efficiency of monitoring parameters, and facilitate more timely acquisition of the state parameters of oilfield equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0043] Figure 1 The diagram is a schematic diagram of an intelligent analysis and fault warning system for oilfield equipment operation status according to the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] The present invention provides an intelligent analysis and fault warning system for oilfield equipment operation status, including a clustering control module and a plurality of wireless sensor nodes;

[0046] The clustering control module is used to divide the distribution range of all wireless sensor nodes into multiple local ranges according to the clustering rules, and to obtain the member nodes and cluster head nodes in each local range respectively, generate clustering results, and send the clustering results to each wireless sensor node;

[0047] Specifically, the clustering control module can perform the above operations according to a set time period, for example, every one week, the distribution range of all wireless sensor nodes is divided into multiple local ranges, the member nodes and cluster head nodes in each local range are obtained respectively, the clustering results are generated, and the clustering results are sent to each wireless sensor node;

[0048] Specifically, in non-first clustering, the clustering result can be transmitted to each wireless sensor node through the communication architecture formed by the previous clustering, and, in the first clustering, the clustering result can be sent to each wireless sensor node through a flooding method;

[0049] The wireless sensor node obtains its own role type and the cluster to which it belongs according to the clustering result; the role type is non-cluster head node or cluster head node; the non-cluster head node is used to obtain the monitoring parameters of the oilfield equipment and transmit them to the cluster head node of the cluster where it is located;

[0050] Specifically, the monitoring parameters include data such as temperature, pressure, flow rate and vibration amplitude of oilfield equipment.

[0051] Among them, the distribution range of all wireless sensor nodes is divided into multiple local ranges according to the clustering rule, including:

[0052] Create a control function:

[0053]

[0054] F(n) represents the control function, n represents the number of local ranges, area i represents the area of ​​the ith local range, area represents the area of ​​the distribution range of all wireless sensor nodes, and dist i represents the average distance between the cluster head node and other cluster head nodes in the i-th local range; the value range of n is [1, N], N represents the total number of wireless sensor nodes; dma represents the maximum distance between any two wireless sensor nodes; α represents the weight;

[0055] The control function of the present invention takes into account the area of ​​the local range and the average distance between the cluster head nodes respectively, which is conducive to reducing the number of local ranges as much as possible through the average area of ​​the local range, and also avoids too few local ranges through the average distance between the cluster head nodes, because this means that when forwarding between cluster head nodes, the number of nodes that can be selected for the next hop is small, which also affects the transmission efficiency. Therefore, the control function of the present invention can achieve a better balance between obtaining the number of local ranges as small as possible and the transmission efficiency, and further improve the transmission efficiency.

[0056] The value of n that makes the control function reach the maximum value is expressed as M;

[0057] The distribution range of all wireless sensor nodes is divided into M local ranges.

[0058] In the process of using the sensor network to monitor the operating status of oilfield equipment and to warn of faults, the present invention does not use a fixed number of local ranges, but establishes a control function and uses the value of n that makes the control function obtain the maximum value as the number of local ranges finally determined. In this way, the number of local ranges can be changed with the change of clustering rules and the state of the wireless sensor node, and the number of local ranges can be more effectively controlled to avoid an excessive number of local ranges, suppress the forwarding times of monitoring parameters, better improve the transmission efficiency of monitoring parameters, and facilitate more timely acquisition of the state parameters of oilfield equipment.

[0059] Preferably, the process of obtaining the maximum value of the distance between any two wireless sensor nodes is as follows:

[0060] S1, number all wireless sensor nodes, starting from 1, with a numbering interval of 1 and a maximum number of N;

[0061] S2, initialize the value of integer b to 1;

[0062] S3, respectively calculating the distance between the wireless sensor node numbered b and each of the remaining wireless sensor nodes;

[0063] S4, store the maximum value of the distance obtained in S3 into the set DM;

[0064] S5, determine whether b is less than N. If so, add 1 to the value of b and enter S3. If not, enter S6.

[0065] S6, taking the maximum value in DM as the maximum value of the distance between any two wireless sensor nodes.

[0066] Specifically, the value range of α may be [0.3, 0.7]. Preferably, the value of α may be 0.5.

[0067] Preferably, it also includes a data transmission and communication module;

[0068] The cluster head node is used to obtain the monitoring parameters of the oilfield equipment and to transmit the monitoring parameters to the data transmission and communication module.

[0069] Specifically, each wireless sensor node of the present invention needs to be responsible for acquiring monitoring parameters. Therefore, after the wireless sensor node serves as the cluster head node, it still needs to acquire monitoring parameters.

[0070] The data transmission and communication module can be arranged within the distribution range of the wireless sensor nodes.

[0071] The data transmission and communication module can be a device with 4G, 5G and other communication capabilities.

[0072] Preferably, transmitting the monitoring parameters to the data transmission and communication module comprises:

[0073] The cluster head node transmits the acquired monitoring parameters of the oil field equipment and the monitoring parameters received from the non-cluster head nodes to the data transmission and communication module.

[0074] Specifically, if the cluster head node can communicate directly with the data transmission and communication module, the monitoring parameters will be sent directly to the data transmission and communication module; if the cluster head node cannot communicate directly with the data transmission and communication module, it will be sent to the surrounding cluster head nodes, continuously forwarded by other cluster head nodes, and finally transmitted to the data transmission and communication module.

[0075] Preferably, it also includes a data storage module;

[0076] The data transmission and communication module is used to transmit the received monitoring parameters to the data storage module;

[0077] The data storage module is used to store monitoring parameters.

[0078] Specifically, the data storage module can be a database in a cloud server or a hard disk device in a local device.

[0079] The data storage module is responsible for storing the monitoring parameters.

[0080] Preferably, it also includes a data preprocessing module;

[0081] The data preprocessing module is used to filter the monitoring parameters newly stored in the data storage module to obtain the filtered monitoring parameters.

[0082] Specifically, filtering can effectively reduce the impact of noise on the subsequent fault diagnosis process. Filtering can be performed by arithmetic mean filtering, recursive mean filtering, and other methods.

[0083] Preferably, it also includes a fault diagnosis module;

[0084] The fault diagnosis module is used to perform intelligent analysis on the filtered monitoring parameters and obtain the diagnosis results of the oilfield equipment.

[0085] Specifically, the fault diagnosis module can obtain the diagnosis result by judging whether the filtered monitoring parameter is within the set value range. If so, the diagnosis result is that the operation is normal; if not, the diagnosis result is that there is an abnormality.

[0086] In other embodiments, the fault diagnosis module is used to input the same type of monitoring parameter sequence within a specified time interval into a pre-trained fault diagnosis model to obtain a diagnosis result.

[0087] The specified time period can be the most recent week.

[0088] The fault diagnosis model trained in advance may be a SVM model.

[0089] The training process of the SVM model is as follows:

[0090] 1. Data preparation

[0091] (1) Collect data:

[0092] Collect data from oilfield equipment sensors or monitoring systems, including any of the following types:

[0093] Vibration data (such as acceleration and velocity signals);

[0094] Temperature data (bearing temperature, oil temperature, etc.);

[0095] Pressure data (hydraulic or pneumatic);

[0096] Current and voltage (such as motor operating parameters);

[0097] Other equipment operating status data (such as speed, load, etc.);

[0098] (2) Data annotation:

[0099] Label the data into:

[0100] Normal operation (label=0);

[0101] Failure(label=1);

[0102] Data labels can be obtained through historical experience, expert knowledge, or equipment failure logs.

[0103] (3) Data preprocessing:

[0104] Data cleaning: remove outliers and noise.

[0105] Normalization / Standardization: Normalize the data (such as Min-Max Scaling) or standardize it (such as Z-score) to eliminate dimensional differences.

[0106] Feature extraction: Extract effective features from the original signal, such as:

[0107] Time domain characteristics: mean, variance, peak factor, skewness, etc.

[0108] Frequency domain characteristics: frequency amplitude, spectrum center, etc. after FFT transformation.

[0109] Time-frequency domain features: wavelet transform, Hilbert transform, etc.

[0110] Feature selection: Use statistical methods (such as PCA) or algorithms (such as Lasso) to select the most important features and reduce the data dimension.

[0111] 2. Build SVM model:

[0112] (1) Select the SVM type:

[0113] The diagnosis result of the present invention is a two-category problem (normal vs. fault), and the standard SVM is selected.

[0114] (2) Kernel function selection:

[0115] Linear kernel function: used when the data is linearly separable.

[0116] Gaussian kernel function (RBF kernel): commonly used and suitable for most nonlinear data.

[0117] Multinomial kernel function: suitable for data with multinomial distribution.

[0118] Sigmoid kernel function: suitable for smooth probability distribution features.

[0119] The present invention can select the Sigmoid kernel function.

[0120] 3. Model training:

[0121] (1) Data division:

[0122] The data is divided into training set, validation set and test set (such as 70% training, 15% validation, 15% test).

[0123] (2) Model parameter setting:

[0124] C parameter (penalty term): controls the degree of relaxation of classification.

[0125] γ parameter (kernel function width): affects the ability of nonlinear classification.

[0126] Use Grid Search or Random Search to optimize these parameters.

[0127] (3) Model training:

[0128] The model is trained using the SVM algorithm using the training set.

[0129] If the amount of data is large, you can consider dimensionality reduction (such as PCA) or use a distributed training framework.

[0130] The goal of SVM model training is to find an optimal hyperplane that maximizes the classification interval. The end of training is usually determined based on the convergence of the optimization algorithm.

[0131] The goal of SVM is to minimize the following objective function:

[0132]

[0133] Among them, ξ k is the slack variable, C is the penalty parameter, wz is the weight vector, and nm is the number of training samples;

[0134] When the value of the objective function changes very little (less than a set threshold, such as (10^{-5})), the training can be considered to have ended.

[0135] Most SVM implementations will have a default convergence threshold.

[0136] Preferably, it also includes an early warning module;

[0137] The early warning module is used to send an alarm message to the operation and maintenance personnel when the diagnosis result shows an abnormality.

[0138] Specifically, the alarm information includes data such as the number and location of the abnormal oilfield equipment, and the time when the abnormality was detected.

[0139] Alarm information can be sent to the client of the device used by the operation and maintenance personnel.

[0140] Preferably, the area of ​​the local range is determined in the following manner:

[0141] Establish a rectangular coordinate system for the distribution range of all wireless sensor nodes;

[0142] Obtain the maximum value x2 of the X-axis coordinate, the minimum value x1 of the X-axis coordinate, the maximum value y2 of the Y-axis coordinate, and the minimum value y1 of the Y-axis coordinate of the distribution range of all wireless sensor nodes in the rectangular coordinate system;

[0143] Let D represent the area to be segmented; for any point in D with coordinates (x, y), the value range of x is [x1, x2] and the value range of y is [y1, y2];

[0144] The length of the local range is Width is

[0145] In the process of determining the final value of n, the present invention changes the size of the local range each time according to the value of n, so as to obtain a local range area that is more in line with the actual situation as much as possible, and avoid the value of n being too large or too small.

[0146] Preferably, disti The acquisition process includes:

[0147] According to the clustering rules, the cluster head nodes in each local range are obtained respectively;

[0148] The average distance dist between the cluster head node and other cluster head nodes in the i-th local range i The calculation formula is:

[0149]

[0150] dto i,j represents the distance between the cluster head node in the ith local range and the jth cluster head node in the set DT, where DT is the set of all cluster head nodes except the cluster head node in the ith local range.

[0151] The average distance can reflect the degree of discreteness of the distribution between cluster heads. The greater the degree of discreteness, the fewer forwarding times are required when transmitting to the data transmission and communication module.

[0152] Preferably, according to the clustering rule, the cluster head nodes in each local range are obtained respectively, including:

[0153] Calculate the transmission quality value of each wireless sensor node in each local range respectively;

[0154] The wireless sensor node with the largest transmission quality value is regarded as the cluster head node in the local range, and the remaining wireless sensor nodes are regarded as non-cluster head nodes in the local range.

[0155] The clustering rule of the present invention is applied after the local range is determined, so that the number of local ranges can affect the clustering result, so that a more reasonable value of n can be determined based on F(n).

[0156] Preferably, respectively calculating the transmission quality value of the wireless sensor node in each local range includes:

[0157] The transmission quality value of the wireless sensor node is calculated using the following formula:

[0158]

[0159] sendval z Indicates the transmission quality value of wireless sensor node z, dtmd z represents the distance between z and the center of the local range where z is located, danl represents the diameter of the circumscribed circle of the local range where z is located, clu represents the set of existing cluster head nodes, distclust z,vrepresents the distance between z and the cluster head node v in clu, nclu represents the total number of cluster head nodes in clu, w1 and w2 are the first distance weight and the second distance weight respectively.

[0160] The calculation formula of the transmission quality value of the present invention can make the wireless sensor node that is closer to the center of the local range and farther from other cluster head nodes have a higher transmission quality value, so that the distance between the cluster head nodes can be larger, which is beneficial to reducing the number of forwarding times required for data forwarding to the data transmission and communication module. In addition, the wireless sensor node close to the center of the local range is selected to serve as the cluster head node, which can reduce the distance difference between the cluster head node and the non-cluster head node after clustering, shorten the communication distance between the non-cluster head node and the cluster head node, and is beneficial to further improve the data transmission efficiency.

[0161] Specifically, the first distance weight and the second distance weight may be 0.3 and 0.7, respectively.

[0162] Preferably, the distribution range of all wireless sensor nodes is divided into M local ranges, including:

[0163] The local ranges obtained when n=M are taken as the M local ranges finally obtained.

[0164] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An intelligent analysis and fault warning system for oilfield equipment operation status, characterized in that: It includes a clustering control module and multiple wireless sensor nodes; The clustering control module is used to divide the distribution range of all wireless sensor nodes into multiple local ranges according to the clustering rules, and to obtain the member nodes and cluster head nodes in each local range respectively, generate clustering results, and send the clustering results to each wireless sensor node; The wireless sensor node obtains its own role type and the cluster to which it belongs according to the clustering result; the role type is non-cluster head node or cluster head node; the non-cluster head node is used to obtain the monitoring parameters of the oilfield equipment and transmit them to the cluster head node of the cluster where it is located; Among them, the distribution range of all wireless sensor nodes is divided into multiple local ranges according to the clustering rule, including: Create a control function: F(n) represents the control function, n represents the number of local ranges, area i represents the area of ​​the ith local range, area represents the area of ​​the distribution range of all wireless sensor nodes, and dist i represents the average distance between the cluster head node and other cluster head nodes in the i-th local range; the value range of n is [1, N], N represents the total number of wireless sensor nodes; dma represents the maximum distance between any two wireless sensor nodes; α represents the weight; The value of n that makes the control function reach the maximum value is expressed as M; The distribution range of all wireless sensor nodes is divided into M local ranges.

2. The intelligent analysis and fault warning system for oilfield equipment operation status according to claim 1 is characterized in that: It also includes a data transmission and communication module; The cluster head node is used to obtain the monitoring parameters of the oilfield equipment and to transmit the monitoring parameters to the data transmission and communication module.

3. The intelligent analysis and fault warning system for oilfield equipment operation status according to claim 2 is characterized in that: Transmit monitoring parameters to the data transmission and communication module, including: The cluster head node transmits the acquired monitoring parameters of the oil field equipment and the monitoring parameters received from the non-cluster head nodes to the data transmission and communication module.

4. The intelligent analysis and fault warning system for oilfield equipment operation status according to claim 2 is characterized in that: Also included is a data storage module; The data transmission and communication module is used to transmit the received monitoring parameters to the data storage module; The data storage module is used to store monitoring parameters.

5. The intelligent analysis and fault warning system for oilfield equipment operation status according to claim 4 is characterized in that: It also includes a data preprocessing module; The data preprocessing module is used to filter the monitoring parameters newly stored in the data storage module to obtain the filtered monitoring parameters.

6. The intelligent analysis and fault warning system for oilfield equipment operation status according to claim 5 is characterized in that: It also includes a fault diagnosis module; The fault diagnosis module is used to perform intelligent analysis on the filtered monitoring parameters and obtain the diagnosis results of the oilfield equipment.

7. The intelligent analysis and fault warning system for oilfield equipment operation status according to claim 6 is characterized in that: It also includes an early warning module; The early warning module is used to send an alarm message to the operation and maintenance personnel when the diagnosis result shows an abnormality.

8. The intelligent analysis and fault warning system for oilfield equipment operation status according to claim 1 is characterized in that: The area of ​​the local range is determined as follows: Establish a rectangular coordinate system for the distribution range of all wireless sensor nodes; Obtain the maximum value x2 of the X-axis coordinate, the minimum value x1 of the X-axis coordinate, the maximum value y2 of the Y-axis coordinate, and the minimum value y1 of the Y-axis coordinate of the distribution range of all wireless sensor nodes in the rectangular coordinate system; Let D represent the area to be segmented; for any point in D with coordinates (x, y), the value range of x is [x1, x2] and the value range of y is [y1, y2]; The length of the local range is Width is 9. The intelligent analysis and fault warning system for oilfield equipment operation status according to claim 8 is characterized in that: dist i The acquisition process includes: According to the clustering rules, the cluster head nodes in each local range are obtained respectively; The average distance dist between the cluster head node and other cluster head nodes in the i-th local range i The calculation formula is: dto i,j represents the distance between the cluster head node in the ith local range and the jth cluster head node in the set DT, where DT is the set of all cluster head nodes except the cluster head node in the ith local range.

10. The intelligent analysis and fault warning system for oilfield equipment operation status according to claim 9, characterized in that: According to the clustering rules, the cluster head nodes in each local range are obtained respectively, including: Calculate the transmission quality value of each wireless sensor node in each local range respectively; The wireless sensor node with the largest transmission quality value is regarded as the cluster head node in the local range, and the remaining wireless sensor nodes are regarded as non-cluster head nodes in the local range.

Images