A fuzzy logic diagnostic processing system and method for rig operation trouble

Abstract

The application discloses a kind of coal mine underground drilling machine fault diagnosis processing system and method, including hardware system and software system, the hardware system includes sensing system, data transmission network, core control system, fault server, execution system and man-machine interaction system;The software system includes data acquisition and preprocessing module, data fusion processing module, drilling machine fault knowledge base, drilling machine fault diagnosis module and drilling machine fault processing module;Compared with existing coal mine drilling machine state monitoring technology, the application is more intelligent, can display whether drilling machine operation state is normal in real time, when drilling machine operation state is not normal, can give fault mode in time automatically, and push corresponding operation suggestion, provide support for realizing automatic intelligent drilling technology.The application provides strong guarantee for real-time mastering drilling machine working state and quickly eliminating drilling machine fault, reduces the operation difficulty of operator and requirement to experience and knowledge.

Description

Technical Field

[0001] This invention belongs to the field of coal mine drilling rig fault diagnosis technology, specifically relating to a system and method for fuzzy logic diagnosis and processing of drilling rig operation faults. Background Technology

[0002] Coal mine drilling rigs are commonly used equipment for efficient underground gas extraction, advanced roof drainage, grouting and reinforcement of the floor's aquitard, and geological exploration for potential disasters. Coal mine drilling rigs are complex pieces of equipment, requiring 2-3 workers during operation. These workers need not only relevant construction experience but also fault diagnosis experience; that is, when abnormalities occur during operation, workers need to promptly identify the cause of the malfunction, find the root cause, and eliminate the problem as quickly as possible. To reduce the skill requirements of construction personnel, developing a coal mine drilling rig with independent fault diagnosis capabilities has become an important need for coal mining machinery enterprises.

[0003] Currently, the types and number of sensors deployed on coal mine drilling rigs are limited, only able to collect data such as hydraulic pressure, oil temperature, fluid level, and the speed and movement of the drilling head at key locations. Furthermore, this acquired data is not fully utilized. In addition, fault diagnosis in coal mine drilling rigs relies on operators' manual experience to determine the location and cause of faults, and cannot achieve autonomous fault diagnosis by processing existing drilling rig sensor data. Therefore, there is an urgent need to research a method and system for autonomous fault diagnosis of coal mine drilling rigs based on current sensor data. Summary of the Invention

[0004] The purpose of this invention is to propose a system and method for fuzzy logic diagnosis and processing of drilling rig operation faults, so as to solve the problem that existing coal mine drilling rigs cannot perform fault diagnosis autonomously and cannot provide fault handling solutions.

[0005] To solve the above problems, the present invention adopts the following technical solution:

[0006] On the one hand, the present invention provides a fault diagnosis and handling system for underground drilling rigs in coal mines, including a hardware system and a software system:

[0007] The hardware system includes a sensing system, a data transmission network, a core control system, a fault server, an execution system, and a human-machine interface system. Specifically: the sensing system includes information probes, hydraulic pressure sensors, hydraulic flow sensors, a body speed sensor, and proximity switches deployed on the coal mine drilling rig; the data transmission network connects the core control module with other modules, including CAN, RS485, and industrial Ethernet; the core control system includes embedded devices for data processing and a PLC controller for drilling rig control; the fault server is a server for storing fault diagnosis experience; the execution system includes hydraulic actuators that control the coal mine drilling rig's movements under the control commands of the core control system; and the human-machine interface system includes an industrial display screen for displaying fault diagnosis and processing results and a remote control for sending control commands to the core control system.

[0008] The software system includes a data acquisition and preprocessing module, a data fusion processing module, a drilling rig fault knowledge base, a drilling rig fault diagnosis module, and a drilling rig fault handling module. The data acquisition and preprocessing module receives and preprocesses electrical control signals, mechanical sensor data, and hydraulic sensor data from the sensing system, and then uploads the processed data to the data fusion processing module. The data fusion processing module processes the currently received data, including identifying the current drilling rig action and calculating the membership degree of abnormal drilling rig action symptoms, and sends the results to the drilling rig fault diagnosis module. The fault knowledge base includes a fault cause information database and a fault cause-symptom database. The system includes an operation suggestion information database; the drilling rig fault diagnosis module receives information from the data fusion processing module, refers to the fault knowledge base, determines the number of the abnormal action and the cause of the faulty equipment, and sends the results to the drilling rig fault handling module; the drilling rig fault handling module receives the fault diagnosis results provided by the drilling rig fault diagnosis module, formulates and executes fault handling strategies based on the operation suggestion information database in the fault knowledge base; wherein, the data acquisition and preprocessing module, the data fusion processing module, the drilling rig fault diagnosis module, and the drilling rig fault handling module are all loaded on the core control system; the drilling rig fault knowledge base is loaded on the fault server.

[0009] Furthermore, the fault cause information database, fault cause-symptom database, and operation suggestion information database are specifically as follows:

[0010] The fault cause information database includes major categories such as electrical control system faults, hydraulic transmission system faults, and mechanical system faults, with each major category including multiple equipment fault causes.

[0011] The fault cause-symptom database is used to store the causal relationship between abnormal drilling rig operations and fault causes, and this relationship is defined as an association information matrix. ,in , , , This represents the total number of causes of drilling rig malfunctions. This represents the total number of actions performed by the drilling rig during the drilling process. Representing the Abnormal signs of drilling rig operation for the first Membership degree of each fault cause;

[0012] The operation suggestion information database includes operation suggestions for abnormal actions and operation suggestions for equipment malfunctions. The operation suggestions for abnormal actions are used to provide the operation strategy to be executed when an action malfunctions, based on the number information of the action currently being performed by the drilling rig. The operation suggestions for equipment malfunctions are used to provide the operation strategy to be executed when an action malfunctions, based on a set of malfunction causes. Determine the corresponding operational strategies for each cause of failure.

[0013] On the other hand, the present invention provides a fuzzy logic diagnosis and processing method for drilling rig operation faults, specifically including the following steps:

[0014] Step 1: Collect data and perform preprocessing and fusion, including the following sub-steps:

[0015] Step 1.1: Acquisition and preprocessing of sensor data;

[0016] Step 1.2: Identify the current action of the drilling rig and obtain the execution probability of each action. ,in, For the first The probability of executing an action. n This represents the total number of actions performed by the drilling rig during construction.

[0017] Step 1.3, Calculation of membership degree of abnormal drilling rig movement symptoms, includes the following operations:

[0018] Step 1.3.1 describes the abnormal state of the drilling rig, obtaining a set of signs of abnormal drilling rig operation. ,in Representing the drilling rig These actions are the corresponding signs of abnormality. This represents the total number of actions performed by the drilling rig during construction.

[0019] Step 1.3.2: Obtain actions from historical data. This is a discrete set of sensor data under normal conditions, specifically: for actions... Historical data under normal conditions is discretized using an equidistant method to obtain the action. Discrete value set under normal conditions ,in Representing the Discrete values ​​of sensor data , The total number of sensor data; discrete value set corresponding actions i signs The membership degree is 0, ;

[0020] Step 1.3.3: Discretize the electrical control signals, mechanical sensor data, and hydraulic sensor data collected in real time when the drilling rig performs the current action using the equidistant method to obtain the discrete value set corresponding to the drilling rig's current action. ,in, Represents the current number Discrete values ​​of sensor data ;

[0021] Step 1.3.4, utilize the discrete value set of the current action. and actions Discrete value set under normal conditions Find the offset distance ,in, , ;set up ,in and Representing the first The values ​​obtained after discretizing the lower and upper limits of the sensor data using the equidistant method; if d i Greater than or equal to The value indicates the current action's effect on the symptom. membership degree The value is 1, otherwise Thus, a set is obtained. ;

[0022] Step 1.3.5, combining the identification results of the drilling rig's current actions. The membership set of the actual samples to the abnormal behavior of the drilling rig at the current moment is calculated as follows: , ;

[0023] Step 2: Diagnosis and handling of abnormal drilling rig movements, including the following sub-steps:

[0024] Step 2.1: The data fusion processing module in Provide the membership set of actual samples for abnormal drilling rig behavior at all times. ,in , ;like middle If it is greater than the first preset threshold, then it is determined that... The drilling rig is currently executing the first... Then determine the corresponding action. μ in xi If it is less than the second preset threshold, then determine the first... If all actions are normal, the fault diagnosis process in this fault diagnosis cycle ends, and the cycle awaits the next fault diagnosis cycle; otherwise, it is considered that the fault diagnosis process ends. If an action is abnormal, obtain the abnormal action number. Proceed to step 2.2;

[0025] Step 2.2: Based on the abnormal action number obtained in Step 2.1, look up the abnormal drilling rig action operation suggestions in the operation suggestion information database. If a solution can be found, proceed to Step 4.1; otherwise, proceed to Step 3.

[0026] Step 3: Troubleshooting and handling of drilling rig equipment, which consists of the following steps:

[0027] Step 3.1: Diagnosis of equipment failure: The membership set of the actual samples at the current moment provided in Step 1 to the abnormal behavior symptoms of the drilling rig. Combined with the correlation information matrix of the fault cause-symptom database provided by the fault knowledge base Calculate the above two data points. ,in Representing fuzzy logic operators, in this embodiment, the following is adopted: , , The total number of causes of equipment failure; thus obtaining the number of causes of failure. The causes of abnormal actions in a collection of drilling rig malfunction causes Membership set ,like The value is greater than Except If all elements are excluded, then determine the first element. The reason for the abnormal action is the first Cause of equipment failure ;

[0028] Step 3.2: Equipment Fault Handling Analysis: Based on the equipment fault causes provided in Step 3.1, the equipment fault handling suggestions in the operation suggestion information database provided by the fault knowledge base are looked up to find the equipment fault handling method under the current situation. If a solution can be found, proceed to Step 4.2; otherwise, proceed to Step 4.3.

[0029] Step 4: Troubleshooting Drilling Rig Malfunctions: This is divided into handling abnormal actions and troubleshooting faulty equipment, as detailed below:

[0030] Step 4.1: Upload the abnormal action number and corresponding solution obtained in Step 2.2 to the display device in the human-machine interaction system, so that the drilling rig repairman can handle the abnormal action according to the displayed solution;

[0031] Step 4.2: Upload the causes of equipment failure and corresponding troubleshooting methods provided in Step 3.2 to the display device in the human-interactive system. The drilling rig repairman can then repair or replace the malfunctioning equipment based on the displayed solutions, thus resolving the drilling rig equipment failure.

[0032] Step 4.3: Upload the equipment failure cause provided in Step 3.2 to the display device in the manual interaction system. The drilling rig repairman will then handle the drilling rig equipment failure and add the corresponding handling method to the operation suggestion information database in the failure server.

[0033] Furthermore, in step 1.1, the specific preprocessing operations are as follows: the data collected by the sensing system is divided into electronic control signals, hydraulic sensing data and mechanical sensing data. Among them, the electronic control signals and mechanical sensing data are filtered out by threshold method to remove erroneous signals. The hydraulic sensing data is first filtered out by threshold method to remove erroneous data, and then the average value method is used to obtain the processed hydraulic sensing data.

[0034] Compared with the prior art, the present invention has the following technical effects:

[0035] Compared with existing coal mine drilling rig status monitoring technologies, the status monitoring and fault prediction of this invention are more intelligent. For example, the fault diagnosis and processing system adds a data fuzzy processing procedure and a fault cause-symptom database, which can deduce abnormal drilling rig operation information and faulty equipment information through fuzzy logic analysis. Based on the above reasoning results, corresponding fault handling suggestions are given, and finally, the fault information and handling suggestions are pushed to the system display device. Therefore, this invention realizes real-time display of whether the drilling rig's operating status is normal. When the drilling rig's operating status is abnormal, it can automatically and promptly give the fault mode and push corresponding operation suggestions, providing support for the realization of automated and intelligent drilling technology. This invention provides a strong guarantee for real-time monitoring of the drilling rig's operating status and rapid troubleshooting of drilling rig faults, reducing the operational difficulty for operators and the requirements for experience and knowledge. Attached Figure Description

[0036] Figure 1 This is an architecture diagram of the fault diagnosis and processing system of the present invention;

[0037] Figure 2 This is a flowchart of the fault diagnosis process of the present invention.

[0038] The present invention will be further explained and described below with reference to the accompanying drawings and specific embodiments. Detailed Implementation

[0039] like Figure 1 As shown, the fault diagnosis and processing system for underground coal mine drilling rigs provided by this invention includes a hardware system and a software system; wherein:

[0040] The hardware system is a collection of supporting hardware for data acquisition, algorithm execution, and strategy processing required for the fault diagnosis process of coal mine drilling rigs. Specifically, it includes a sensing system, a data transmission network, a core control system, a fault server, an execution system, and a human-machine interface system. Specifically: the sensing system includes information probes, hydraulic pressure sensors, hydraulic flow sensors, body speed sensors, and proximity switches deployed on the coal mine drilling rig; the data transmission network connects the core control module with other modules, including CAN, RS485, and industrial Ethernet; the core control system includes embedded devices for data processing and a PLC controller for drilling rig control; the fault server is a server for storing fault diagnosis experience (i.e., a fault knowledge base); the execution system includes hydraulic actuators that control the actions of the coal mine drilling rig under the control commands of the core control system; and the human-machine interface system includes an industrial display screen for displaying fault diagnosis results and a remote control for sending control commands to the core control system.

[0041] The software system refers to the runtime environment for the algorithms required in the fault diagnosis process, including a data acquisition and preprocessing module, a data fusion processing module, a drilling rig fault knowledge base, a drilling rig fault diagnosis module, and a drilling rig fault handling module. The data acquisition and preprocessing module receives and preprocesses electrical control signals, mechanical sensor data, and hydraulic sensor data from the sensing system, and then uploads the processed data to the data fusion processing module. The data fusion processing module processes the currently received data, including identifying the current actions of the drilling rig, calculating the membership degree of abnormal drilling rig actions, and sending the results to the drilling rig fault diagnosis module. The fault knowledge base includes a fault cause information database, a fault cause-symptom database, and an operation suggestion information database. The fault knowledge base can be manually added to, corrected, and deleted during operation. The drilling rig fault diagnosis module receives information from the data fusion processing module, refers to the fault knowledge base, determines the number of abnormal actions and the cause of the faulty equipment, and sends the results to the drilling rig fault handling module. The drilling rig fault handling module receives the fault diagnosis results from the drilling rig fault diagnosis module, formulates fault handling strategies based on the operation suggestion information database in the fault knowledge base, and executes them. The data acquisition and preprocessing module, data fusion processing module, drilling rig fault diagnosis module, and drilling rig fault handling module are all loaded onto the core control system; the drilling rig fault knowledge base is loaded onto the fault server.

[0042] The aforementioned fault knowledge base includes a fault cause information base, a fault cause-symptom base, and an operation suggestion information base, each of which contains the following content:

[0043] (1) The fault cause information database includes major categories such as electrical control system faults, hydraulic transmission system faults, and mechanical system faults. Each major category includes multiple equipment fault causes.

[0044] Specifically, Failure Mode, Mechanism and Effects Analysis (FMECA) can be used to study drilling rigs, identify common equipment failure causes leading to abnormal drilling rig operation, and define this set of causes as... ,in Indicates the first One cause of the malfunction, This represents the total number of causes of drilling rig malfunctions.

[0045] (2) The fault cause-symptom database describes the causal relationship between abnormal drilling rig operation and fault causes. This relationship is defined here as the correlation information matrix. ,in , , , This represents the total number of causes of drilling rig malfunctions. This represents the total number of actions performed by the drilling rig during operation. Representing the Abnormal signs of drilling rig operation for the first The membership degree of each fault cause.

[0046] Specifically, experience is used to assign corresponding scores to the causes of each abnormal action of the drilling rig, and the weight of each cause is assigned empirically according to its importance. Then, the scores and weights are normalized to obtain the result. Abnormal signs of drilling rig operation for the first Membership value of each reason .

[0047] (3) The operation suggestion information database includes operation suggestions for abnormal actions and operation suggestions for equipment failures. The operation suggestions for abnormal actions are used to provide the operation strategy (i.e., solution) to be performed when the action is abnormal, such as correcting the action execution status, returning to the initial state of the drilling rig, or emergency shutdown, based on the number information of the action currently being performed by the drilling rig. The operation suggestions for equipment failures are used to provide the operation strategy (i.e., solution) to be performed when the action is abnormal, such as correcting the action execution status, returning to the initial state of the drilling rig, or emergency shutdown. Determine the corresponding operational strategies for each cause of failure, such as electrical circuit repair, replacement of hydraulic components, and inspection of the main equipment.

[0048] Specifically, taking the slewing rotation of a drilling rig as an example, there are several scenarios: a) If the control parameter value is too low, the slewing pressure is too low, and the drill rod speed is too slow, diagnosis reveals that the abnormal drilling action originates from an abnormal control signal. In this case, the abnormal action operation suggestion determines whether to correct the action execution algorithm. b) If the control parameters are normal, the slewing pressure is low, and the drill rod speed is slow, diagnosis reveals a possible problem with the hydraulic pipeline. In this case, the equipment fault operation suggestion determines that an emergency shutdown is necessary to check whether the hydraulic pipeline of the slewing motor is ruptured or the pipe joint is loose, causing oil leakage. The above is just a specific hypothetical case, and the causes of failure and operation suggestions are not fully listed. The expert knowledge base can be added, modified, and deleted based on various failures that occur during actual drilling rig operation, making the expert knowledge base increasingly complete.

[0049] like Figure 2 As shown, the fuzzy logic diagnosis and processing method for drilling rig operation faults provided by this invention specifically includes the following steps:

[0050] Step 1: Collect data and perform preprocessing and fusion. This includes the following sub-steps:

[0051] Step 1.1: Acquisition and preprocessing of sensor data.

[0052] Specifically, the data collected by the sensing system is divided into electronic control signals, hydraulic sensing data, and mechanical sensing data. Therefore, a threshold method is needed to filter the electronic control signals and mechanical sensing data to remove erroneous signals. Hydraulic sensing data is a continuous variable, and its values ​​fluctuate; therefore, a threshold method is first used to filter out erroneous data in the hydraulic sensing data, and then an averaging method is used to obtain the processed hydraulic sensing data.

[0053] Step 1.2, Identification of the current action of the drilling rig.

[0054] A hierarchical Bayesian network is used to establish a reasoning model for drilling rig operation. Specifically, the drilling rig equipment, electrical control circuit, hydraulic circuit, and drilling rig actions are defined as nodes in the Bayesian network. Then, based on experience and the drilling rig's structure, the conditional occurrence probabilities of the nodes in the Bayesian network are assigned values ​​to establish a Bayesian model for drilling rig action reasoning. The preprocessed electrical control signals, mechanical sensor data, and hydraulic sensor data obtained in step 1.1 map the operating state of the drilling rig equipment. This information is used as input to the Bayesian model to obtain the execution probability of each drilling rig action. .in, For the first The probability of executing an action. n This represents the total number of actions performed by the drilling rig during construction.

[0055] Step 1.3, Calculation of membership degree for abnormal drilling rig movement symptoms. This specifically includes the following operations:

[0056] Step 1.3.1 describes the abnormal state of the drilling rig, obtaining a set of signs of abnormal drilling rig operation. ,in Representing the drilling rig These actions are the corresponding signs of abnormality. This represents the total number of actions performed by the drilling rig during construction.

[0057] Step 1.3.2: Obtain actions from historical data. This is a discrete set of sensor data under normal conditions, specifically: for actions... Historical data under normal conditions is discretized using an equidistant method to obtain the action. Discrete value set under normal conditions ,in Representing the Discrete values ​​of sensor data , This represents the total amount of sensor data. Discrete value set. corresponding actions i signs The membership degree is 0, .

[0058] Step 1.3.3: Discretize the electrical control signals, mechanical sensor data, and hydraulic sensor data collected in real time when the drilling rig performs the current action using the equidistant method to obtain the discrete value set corresponding to the drilling rig's current action. ,in, Represents the current number Discrete values ​​of sensor data .

[0059] Step 1.3.4, utilize the discrete value set of the current action. and actions Discrete value set under normal conditions Find the offset distance ,in, , .set up ,in and Representing the first The values ​​obtained by discretizing the lower and upper limits of the sensor data using the equidistant method. If d i Greater than or equal to The value indicates the current action's effect on the symptom. membership degree The value is 1, otherwise Thus, a set is obtained. .

[0060] Step 1.3.5, combining the identification results of the drilling rig's current actions. The membership set of the actual samples to the abnormal behavior of the drilling rig at the current moment is calculated as follows: , .

[0061] Step 2: Diagnosis and handling of abnormal drilling rig movements, including the following sub-steps:

[0062] Step 2.1: The data fusion processing module in Provide the membership set of actual samples for abnormal drilling rig behavior at all times. ,in , .like middle If it is greater than the first preset threshold, then it is determined that... The drilling rig is currently executing the first... Then determine the corresponding action. μ in xi If it is less than the second preset threshold, then determine the first... If all actions are normal, the fault diagnosis process in this fault diagnosis cycle ends, and the cycle awaits the next fault diagnosis cycle. Otherwise, it is considered that the first... If an action is abnormal, obtain the abnormal action number. Proceed to step 2.2. The preset threshold is determined based on experience.

[0063] Step 2.2: Based on the abnormal action number obtained in Step 2.1, look up the abnormal drilling rig action operation suggestions in the operation suggestion information database. If a solution can be found, proceed to Step 4.1; otherwise, proceed to Step 3.

[0064] Step 3: Troubleshooting and handling of drilling rig equipment, which consists of the following steps:

[0065] Step 3.1: Diagnosis of equipment failure: The membership set of the actual samples at the current moment provided in Step 1 to the abnormal behavior symptoms of the drilling rig. Combined with the correlation information matrix of the fault cause-symptom database provided by the fault knowledge base Calculate the above two data points. ,in Representing fuzzy logic operators, in this embodiment, the following is adopted: , , This represents the total number of causes of equipment failure. From this, we can obtain the number of causes leading to the [missing information]. The causes of abnormal actions in a collection of drilling rig malfunction causes Membership set ,like The value is greater than Except If all elements are excluded, then determine the first element. The reason for the abnormal action is the first Cause of equipment failure .

[0066] Step 3.2: Equipment Fault Handling Analysis. Specifically, based on the equipment fault causes provided in Step 3.1, the equipment fault handling suggestions in the operation suggestion information database provided by the fault knowledge base are looked up to find the equipment fault handling method under the current situation. If a solution can be found, proceed to Step 4.2; otherwise, proceed to Step 4.3.

[0067] Step 4: Troubleshooting Drilling Rig Malfunctions: This is divided into handling abnormal actions and troubleshooting faulty equipment, as detailed below:

[0068] Step 4.1: Upload the abnormal action number and corresponding solution obtained in Step 2.2 to the display device in the manual interaction system. The drilling rig repairman will then handle the abnormal action according to the displayed solution, such as correcting the action execution status, returning to the initial action status, or performing an emergency shutdown.

[0069] Step 4.2: Upload the equipment failure cause and corresponding equipment failure handling method provided in Step 3.2 to the display device in the manual interaction system. The drilling rig repairman can then repair or replace the failed equipment according to the displayed solution, thereby realizing the handling of drilling rig equipment failure.

[0070] Step 4.3: Upload the equipment failure cause provided in Step 3.2 to the display device in the manual interaction system. The drilling rig repairman will then handle the drilling rig equipment failure based on experience and add the corresponding handling method to the operation suggestion information database in the failure server.

[0071] Compared with existing coal mine drilling rig status monitoring technologies, the status monitoring and fault prediction system and method of this invention are more intelligent. They can display the drilling rig's operational status in real time, and when the drilling rig's operational status is abnormal, they can automatically and promptly identify the fault mode and push corresponding operational suggestions, providing support for the realization of automated and intelligent drilling technology. This invention provides a strong guarantee for real-time monitoring of the drilling rig's operating status and rapid troubleshooting, reducing the operational difficulty for operators and the experience and knowledge requirements.

Claims

1. A fault diagnosis and handling system for underground drilling rigs in coal mines, comprising a hardware system and a software system, characterized in that: The hardware system includes a sensing system, a data transmission network, a core control system, a fault server, an execution system, and a human-machine interface system. Specifically: the sensing system includes information probes, hydraulic pressure sensors, hydraulic flow sensors, a body speed sensor, and proximity switches deployed on the coal mine drilling rig; the data transmission network connects the core control module with other modules, including CAN, RS485, and industrial Ethernet; the core control system includes embedded devices for data processing and a PLC controller for drilling rig control; the fault server is a server for storing fault diagnosis experience; the execution system includes hydraulic actuators that control the coal mine drilling rig's movements under the control commands of the core control system; and the human-machine interface system includes an industrial display screen for displaying fault diagnosis and processing results and a remote control for sending control commands to the core control system. The software system includes a data acquisition and preprocessing module, a data fusion processing module, a drilling rig fault knowledge base, a drilling rig fault diagnosis module, and a drilling rig fault handling module. The data acquisition and preprocessing module receives and preprocesses electrical control signals, mechanical sensor data, and hydraulic sensor data from the sensing system, and then uploads the processed data to the data fusion processing module. The data fusion processing module processes the currently received data, including identifying the current drilling rig action and calculating the membership degree of abnormal drilling rig action symptoms, and sends the results to the drilling rig fault diagnosis module. The fault knowledge base includes a fault cause information database and a fault cause-symptom database. The system includes an operation suggestion information database; the drilling rig fault diagnosis module receives information from the data fusion processing module, refers to the fault knowledge base, determines the number of the abnormal action and the cause of the faulty equipment, and sends the results to the drilling rig fault handling module; the drilling rig fault handling module receives the fault diagnosis results provided by the drilling rig fault diagnosis module, formulates and executes fault handling strategies based on the operation suggestion information database in the fault knowledge base; wherein, the data acquisition and preprocessing module, the data fusion processing module, the drilling rig fault diagnosis module, and the drilling rig fault handling module are all loaded on the core control system; the drilling rig fault knowledge base is loaded on the fault server; The data acquisition and preprocessing module operates as follows: Step 1: Collect data and perform preprocessing and fusion, including the following sub-steps: Step 1.1: Acquisition and preprocessing of sensor data; Step 1.2: Identify the current action of the drilling rig and obtain the execution probability of each action. ,in, For the first The probability of executing an action. n This represents the total number of actions performed by the drilling rig during construction. Step 1.3, Calculation of membership degree for abnormal drilling rig movement symptoms, includes the following operations: Step 1.3.1 describes the abnormal state of the drilling rig, obtaining a set of signs of abnormal drilling rig operation. ,in Representing the drilling rig These actions are the corresponding signs of abnormality. This represents the total number of actions performed by the drilling rig during construction. Step 1.3.2: Obtain actions from historical data. This is a discrete set of sensor data under normal conditions, specifically: for actions... Historical data under normal conditions is discretized using an equidistant method to obtain the action. Discrete value set under normal conditions ,in Representing the Discrete values ​​of sensor data , The total number of sensor data; discrete value set Corresponding actions i signs The membership degree is 0, ; Step 1.3.3: Discretize the electrical control signals, mechanical sensor data, and hydraulic sensor data collected in real time when the drilling rig performs the current action using the equidistant method to obtain the discrete value set corresponding to the drilling rig's current action. ,in, Represents the current number Discrete values ​​of sensor data ; Step 1.3.4, utilize the discrete value set of the current action. and actions Discrete value set under normal conditions Find the offset distance ,in, , ;set up ,in and Representing the first The values ​​obtained after discretizing the lower and upper limits of the sensor data using the equidistant method; if d i Greater than or equal to The value indicates the current action's effect on the symptom. membership degree The value is 1, otherwise Thus, a set is obtained. ; Step 1.3.5, combining the identification results of the drilling rig's current actions. The membership set of the actual samples to the abnormal signs of drilling rig movement at the current moment is calculated as follows: , ; The data fusion processing module operates as follows: Step 2.1: The data fusion processing module in Provide the membership set of actual samples for abnormal drilling rig behavior at all times. ,in , ;like middle If it is greater than the first preset threshold, then it is determined that... The drilling rig is currently executing the first... Then determine the corresponding action. μ in xi If it is less than the second preset threshold, then determine the first... If the first action is normal, the fault diagnosis process in the current fault diagnosis cycle ends, and the process waits for the next fault diagnosis cycle; otherwise, it is considered that the first action is normal. If an action is abnormal, obtain the abnormal action number. Proceed to step 2.2; Step 2.2: Based on the abnormal action number obtained in Step 2.1, look up the abnormal drilling rig action operation suggestions in the operation suggestion information database. If a solution can be found, proceed to Step 4.1; otherwise, proceed to Step 3. The operation of the drilling rig fault diagnosis module is as follows: Step 3.1: Diagnosis of equipment failure: The membership set of the actual samples at the current moment provided in Step 1 to the abnormal behavior symptoms of the drilling rig. Combined with the correlation information matrix of the fault cause-symptom database provided by the fault knowledge base Calculate the above two data points. ,in Represents fuzzy logic operators, using , , The total number of causes of equipment failure; thus obtaining the number of causes of failure. The causes of abnormal actions in a collection of drilling rig malfunction causes Membership set ,like The value is greater than Except If all elements are excluded, then determine the first element. The reason for the abnormal action is the first Causes of equipment failure ; Step 3.2: Equipment Fault Handling Analysis: Based on the equipment fault causes provided in Step 3.1, the equipment fault handling suggestions in the operation suggestion information database provided by the fault knowledge base are looked up to find the equipment fault handling method under the current situation. If a solution can be found, proceed to Step 4.2; otherwise, proceed to Step 4.

3. The operation of the drilling rig fault handling module is divided into handling abnormal actions and handling faulty equipment, as detailed below: Step 4.1: Upload the abnormal action number and corresponding solution obtained in Step 2.2 to the display device in the human-machine interaction system, so that the drilling rig repairman can handle the abnormal action according to the displayed solution; Step 4.2: Upload the causes of equipment failure and corresponding troubleshooting methods provided in Step 3.2 to the display device in the human-interactive system. The drilling rig repairman can then repair or replace the malfunctioning equipment based on the displayed solutions, thus resolving the drilling rig equipment failure. Step 4.3: Upload the equipment failure cause provided in Step 3.2 to the display device in the manual interaction system. The drilling rig repairman will then handle the drilling rig equipment failure and add the corresponding handling method to the operation suggestion information database in the failure server.

2. The fault diagnosis and processing system for underground coal mine drilling rigs as described in claim 1, characterized in that, The fault cause information database, fault cause-symptom database, and operation suggestion information database are as follows: The fault cause information database includes major categories such as electrical control system faults, hydraulic transmission system faults, and mechanical system faults, with each category including multiple equipment fault causes. The fault cause-symptom database is used to store the causal relationship between abnormal drilling rig operations and fault causes, and this relationship is defined as an association information matrix. ,in , , , This represents the total number of causes of drilling rig malfunctions. This represents the total number of actions performed by the drilling rig during the drilling process. Representing the Abnormal signs of drilling rig operation Membership degree of each fault cause; The operation suggestion information database includes operation suggestions for abnormal actions and operation suggestions for equipment malfunctions. The operation suggestions for abnormal actions are used to provide the operation strategy to be executed when an action malfunctions, based on the number information of the action currently being performed by the drilling rig. The operation suggestions for equipment malfunctions are used to provide the operation strategy to be executed when an action malfunctions, based on a set of malfunction causes. Determine the corresponding operational strategies for each cause of the failure.

3. A method for fuzzy logic diagnosis and processing of drilling rig operation faults, characterized in that, Specifically, the steps include the following: Step 1: Collect data and perform preprocessing and fusion, including the following sub-steps: Step 1.1: Acquisition and preprocessing of sensor data; Step 1.2: Identify the current action of the drilling rig and obtain the execution probability of each action. ,in, For the first The probability of executing an action. n This represents the total number of actions performed by the drilling rig during construction. Step 1.3, Calculation of membership degree for abnormal drilling rig movement symptoms, includes the following operations: Step 1.3.1 describes the abnormal state of the drilling rig, obtaining a set of signs of abnormal drilling rig operation. ,in Representing the drilling rig These actions are the corresponding signs of abnormality. This represents the total number of actions performed by the drilling rig during construction. Step 1.3.2: Obtain actions from historical data. This is a discrete set of sensor data under normal conditions, specifically: for actions... Historical data under normal conditions is discretized using an equidistant method to obtain the action. Discrete value set under normal conditions ,in Representing the Discrete values ​​of sensor data , The total number of sensor data; discrete value set Corresponding actions i signs The membership degree is 0, ; Step 1.3.3: Discretize the electrical control signals, mechanical sensor data, and hydraulic sensor data collected in real time when the drilling rig performs the current action using the equidistant method to obtain the discrete value set corresponding to the drilling rig's current action. ,in, Represents the current number Discrete values ​​of sensor data ; Step 1.3.4, utilize the discrete value set of the current action. and actions Discrete value set under normal conditions Find the offset distance ,in, , ;set up ,in and Representing the first The values ​​obtained after discretizing the lower and upper limits of the sensor data using the equidistant method; if d i Greater than or equal to The value indicates the current action's effect on the symptom. membership degree The value is 1, otherwise Thus, a set is obtained. ; Step 1.3.5, combining the identification results of the drilling rig's current actions. The membership set of the actual samples to the abnormal signs of drilling rig movement at the current moment is calculated as follows: , ; Step 2: Diagnosis and handling of abnormal drilling rig movements, including the following sub-steps: Step 2.1: The data fusion processing module in Provide the membership set of actual samples for abnormal drilling rig behavior at all times. ,in , ;like middle If it is greater than the first preset threshold, then it is determined that... The drilling rig is currently executing the first... Then determine the corresponding action. μ in xi If it is less than the second preset threshold, then determine the first... If the first action is normal, the fault diagnosis process in the current fault diagnosis cycle ends, and the process waits for the next fault diagnosis cycle; otherwise, it is considered that the first action is normal. If an action is abnormal, obtain the abnormal action number. Proceed to step 2.2; Step 2.2: Based on the abnormal action number obtained in Step 2.1, look up the abnormal drilling rig action operation suggestions in the operation suggestion information database. If a solution can be found, proceed to Step 4.1; otherwise, proceed to Step 3. Step 3: Troubleshooting and handling of drilling rig equipment, which consists of the following steps: Step 3.1: Diagnosis of equipment failure: The membership set of the actual samples at the current moment provided in Step 1 to the abnormal behavior symptoms of the drilling rig. Combined with the correlation information matrix of the fault cause-symptom database provided by the fault knowledge base Calculate the above two data points. ,in Represents fuzzy logic operators, using , , The total number of causes of equipment failure; thus obtaining the number of causes of failure. The causes of abnormal actions in a collection of drilling rig malfunction causes Membership set ,like The value is greater than Except If all elements are excluded, then determine the first element. The reason for the abnormal action is the first Causes of equipment failure ; Step 3.2: Equipment Fault Handling Analysis: Based on the equipment fault causes provided in Step 3.1, the equipment fault handling suggestions in the operation suggestion information database provided by the fault knowledge base are looked up to find the equipment fault handling method under the current situation. If a solution can be found, proceed to Step 4.2; otherwise, proceed to Step 4.

3. Step 4: Troubleshooting Drilling Rig Malfunctions: This is divided into handling abnormal actions and troubleshooting faulty equipment, as detailed below: Step 4.1: Upload the abnormal action number and corresponding solution obtained in Step 2.2 to the display device in the human-machine interaction system, so that the drilling rig repairman can handle the abnormal action according to the displayed solution; Step 4.2: Upload the causes of equipment failure and corresponding troubleshooting methods provided in Step 3.2 to the display device in the human-interactive system. The drilling rig repairman can then repair or replace the malfunctioning equipment based on the displayed solutions, thus resolving the drilling rig equipment failure. Step 4.3: Upload the equipment failure cause provided in Step 3.2 to the display device in the manual interaction system. The drilling rig repairman will then handle the drilling rig equipment failure and add the corresponding handling method to the operation suggestion information database in the failure server.

4. The fuzzy logic diagnosis and processing method for drilling rig operation faults as described in claim 3, characterized in that, In step 1.1, the specific preprocessing operations are as follows: the data collected by the sensing system is divided into electronic control signals, hydraulic sensing data and mechanical sensing data. Among them, the electronic control signals and mechanical sensing data are filtered out by threshold method to remove erroneous signals. The hydraulic sensing data is first filtered out by threshold method to remove erroneous data, and then the average value method is used to obtain the processed hydraulic sensing data.

Images