A method for detecting a failure of a sand mixing device

Abstract

This application relates to a fault detection method for sand mixing equipment. It involves detecting the status of various actuators and detection components, namely the pump body and sensors, and performing high-precision fault diagnosis based on an AI fault diagnosis model. A database is used for data storage, feature extraction, and model iteration, thereby improving the real-time performance, accuracy, and scalability of sensor fault detection. This method accurately identifies the functional integrity of key components before equipment startup. If a fault occurs during operation, the control system can determine the location of the specific abnormal component through the fault diagnosis results, automatically switching the control mode to ensure the normal operation of the sand mixing equipment system. This significantly reduces the risks of on-site construction operations, increases the stability of on-site construction, and greatly reduces the labor intensity and construction costs for on-site personnel.

Description

Technical Field

[0001] This application relates to the field of well site fracturing technology, and in particular to a fault detection method for sand mixing equipment. Background Technology

[0002] In existing technologies, commonly used sand mixing equipment at well sites, including diesel-driven and electric-driven sand mixing equipment, typically employs a suction pump, a mixing tank, a discharge pump, and several supporting dry and liquid additive systems to supply fluid to downstream fracturing equipment. Since the sand mixing equipment is the core component of the entire fracturing operation, a malfunction in the sand mixing equipment can prevent the entire fracturing operation from proceeding normally, and may even lead to the failure of the entire operation if the sand mixing equipment malfunctions during the operation.

[0003] During long-term operation, the sensors and other components used on the equipment are easily affected by environmental conditions (such as changes in temperature and humidity), hardware aging, signal transmission loss, and other factors, which can lead to problems such as data drift, no response, and excessive error.

[0004] Traditional sensor fault detection methods often rely on regular manual inspections or simple threshold judgments, which results in defects such as detection lag, high false positive rate, and inability to adapt to complex scenarios. Summary of the Invention

[0005] This application provides a fault detection method for sand mixing equipment to solve the problems of existing technology, such as detection lag, high misjudgment rate and inability to adapt to complex scenarios, which are caused by manual inspection of sensor fault conditions.

[0006] This application provides a fault detection method for sand mixing equipment, including the following steps: The control system reads the working status parameters of each actuator and detection component in the sand mixing equipment system; The control system calls the AI ​​fault diagnosis model to calculate and analyze the read working status parameters to determine whether there is a fault. If the AI ​​fault diagnosis model identifies and determines that there is a fault in the read working status parameters, it determines the fault feature in the fault list corresponding to the fault condition, and outputs the corresponding fault diagnosis result based on the determined fault feature. The control system receives the fault diagnosis results and adjusts the sand mixing equipment system accordingly, switching the working mode of the sand mixing equipment system pipeline.

[0007] Furthermore, after receiving the working status parameters, the host computer matches and binds the fault conditions judged by the AI ​​fault diagnosis model with the corresponding working status parameters, and stores them in the database as new fault data.

[0008] Furthermore, the AI ​​fault diagnosis model is trained through deep learning based on historical fault data in the database.

[0009] Furthermore, the specific steps of the AI ​​fault diagnosis model in identifying the received working status parameters are as follows: The working status parameters are compared and analyzed with the normal working parameters in the database, and data that differs from the normal working parameters are marked as suspected fault data. Feature extraction is performed on suspected fault data, and the extracted features are matched with the fault list to determine the fault characteristics; The fault diagnosis results are output based on the fault characteristics.

[0010] Furthermore, when extracting features from suspected fault data, the extracted features include the data fluctuation frequency and the magnitude of sudden changes.

[0011] Furthermore, the fault diagnosis results include fault type, fault confidence level, and fault occurrence time.

[0012] Furthermore, the fault type corresponds to the fault characteristics in the fault list, and the fault type includes: hardware abnormality fault, signal abnormality fault, and data abnormality fault.

[0013] Furthermore, the specific steps for the control system to receive fault diagnosis results and adjust the sand mixing equipment system based on the fault diagnosis results are as follows: The on / off status of each pipeline in the sand mixing equipment system is switched by adjusting the flow conditions, and the faulty actuators or detection components are isolated, so that the pipelines bypass the faulty actuators or detection components to form new paths, thereby adjusting the working mode of the sand mixing equipment system pipelines.

[0014] The technical solutions provided in this application have the following advantages compared with the prior art: The method provided in this application improves the real-time performance, accuracy, and scalability of sensor fault detection by detecting the status of various execution and detection components, namely the pump body and sensors, and performing high-precision fault diagnosis based on an AI fault diagnosis model. It also utilizes a database to realize data storage, feature extraction, and model iteration, thereby accurately identifying whether the functions of each key component are intact before the equipment is started.

[0015] In addition, if a malfunction occurs during operation, the control system can determine the location of the specific abnormal component through the fault diagnosis results, automatically switch the control mode, ensure the normal operation of the sand mixing equipment system, greatly reduce the risks of on-site construction operations, increase the stability of on-site construction, and greatly reduce the labor intensity and construction costs of on-site personnel. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0019] Figure 1 This is a schematic diagram of the pipeline connection status of the sand mixing equipment system.

[0020] Figure 2 This is a flowchart of the data transmission process. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] The following disclosure provides numerous different embodiments or examples for implementing various structures of this application. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of this application. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0023] For ease of description, spatial relative terms may be used in the text to describe the relative position or movement of one element or feature relative to another element or feature, as shown in the figure. These relative terms include, for example, "inside," "outside," "middle," "outer," "below," "below," "above," "front," "back," etc. Such spatial relative terms are intended to include different orientations of the device in use or operation, other than those depicted in the figure. For example, if the device in the figure undergoes a positional flip, orientation change, or change of motion, these directional indications will change accordingly. For instance, an element described as "below other elements or features" or "below other elements or features" will subsequently be oriented "above other elements or features" or "above other elements or features." Therefore, the example term "below" can include both upper and lower orientations. The device may be otherwise oriented (rotated 90 degrees or in other directions), and the spatial relative descriptors used in the text will be interpreted accordingly.

[0024] To address the shortcomings of existing technologies that rely on manual inspection of sensor malfunctions, such as detection lag, high false positive rates, and inability to adapt to complex scenarios, this application provides a fault detection method for sand mixing equipment. By detecting the status of each pump and sensor, and performing high-precision fault diagnosis based on AI algorithms, and utilizing a database for data storage, feature extraction, and model iteration, the method improves the real-time performance, accuracy, and scalability of sensor fault detection, accurately identifying the functionality of key components before equipment startup.

[0025] This application provides a fault detection method for a sand mixing equipment, comprising the following steps: The control system reads the working status parameters of each actuator and detection component in the sand mixing equipment system; The control system calls the AI ​​fault diagnosis model to calculate and analyze the read working status parameters to determine whether there is a fault. If the AI ​​fault diagnosis model identifies and determines that there is a fault in the read working status parameters, it determines the fault feature in the fault list corresponding to the fault condition, and outputs the corresponding fault diagnosis result based on the determined fault feature. The control system receives the fault diagnosis results and adjusts the sand mixing equipment system accordingly, switching the working mode of the sand mixing equipment system pipeline.

[0026] In some embodiments, after receiving the working status parameters, the host computer matches and binds the fault conditions judged by the AI ​​fault diagnosis model with the corresponding working status parameters and stores them in the database as new fault data.

[0027] In some embodiments, the AI ​​fault diagnosis model is trained using deep learning based on historical fault data in the database.

[0028] In some embodiments, the specific steps of the AI ​​fault diagnosis model in identifying the received working status parameters are as follows: The working status parameters are compared and analyzed with the normal working parameters in the database, and data that differs from the normal working parameters are marked as suspected fault data. Feature extraction is performed on suspected fault data, and the extracted features are matched with the fault list to determine the fault characteristics; The fault diagnosis results are output based on the fault characteristics.

[0029] In some embodiments, when extracting features from suspected fault data, the extracted features include the data fluctuation frequency and the magnitude of sudden changes.

[0030] The frequency of data fluctuations can be analyzed to assess the stability of components during operation and to determine whether fluctuating failures will occur, thus classifying the failure as either intermittent or persistent. The magnitude of sudden changes can analyze the severity of component failures, thereby determining whether replacement of the faulty component is necessary.

[0031] In some embodiments, the fault diagnosis results include fault type, fault confidence level, and fault occurrence time.

[0032] Based on the fault type, operators can easily perform corresponding maintenance or replacement of faulty components, reducing the time spent on troubleshooting and effectively improving overall maintenance efficiency. After a fault occurs, analysis and calculation based on fault characteristics such as data fluctuation frequency and abrupt change amplitude can determine the fault confidence level, allowing operators to judge the fault, predict potential faults in advance, and thus help arrange preventative maintenance, improving efficiency and reducing losses. The fault occurrence time can predict when a fault might occur, facilitating timely handling by operators, or allowing them to know the occurrence time of a past fault, thus tracing the losses caused by that fault.

[0033] In some embodiments, the fault type corresponds to the fault feature in the fault list, and the fault type includes: hardware abnormality fault, signal abnormality fault, and data abnormality fault. The fault types corresponding to the execution unit and the detection unit are not necessarily the same. Different fault features can be established in the database to facilitate the AI ​​fault diagnosis model to call and analyze them.

[0034] In some embodiments, the specific steps for the control system to receive fault diagnosis results and adjust the sand mixing equipment system according to the fault diagnosis results are as follows: The on / off status of each pipeline in the sand mixing equipment system is switched by adjusting the flow conditions, and the faulty actuators or detection components are isolated, so that the pipelines bypass the faulty actuators or detection components to form new paths, thereby adjusting the working mode of the sand mixing equipment system pipelines.

[0035] Please see Figure 1 , Figure 2 In the embodiments provided in this application, the sand mixing equipment system includes a control system, a host computer (HMI), actuators, and detection components. The main actuators include suction pump P1, suction pump P2, discharge pump P3, discharge pump P4, mixing tanks T1 and T2, flow control valves V15 and V16, and several butterfly valves V1-V14. The main detection components include pressure sensors, level sensors, and flow sensors. The sand mixing equipment system also includes sand supply systems S1 and S2, which can be integrated into the equipment or supplied via external equipment. LA1 is a liquid additive system, and DA1 is a dry additive system, used to provide liquid or solid additives to the sand mixing equipment system.

[0036] Pressure sensors are installed at the intake and discharge manifolds of the sand mixing equipment system to detect the intake and discharge pressures. Flow sensors are also installed at both the intake and discharge manifolds to monitor the liquid flow rate within the manifolds. Two level sensors are installed in each of the mixing tanks T1 and T2, with one in operation and the other as a backup. This ensures that if a malfunction is detected in one level sensor using the method provided in this application, the system can quickly switch to the fault-free sensor to perform the detection work, achieving seamless switching and meeting the requirement of continuous operation of the sand mixing equipment.

[0037] In this embodiment, the control system's acquisition module reads the operating status parameters of the suction pump P1, suction pump P2, discharge pump P3, and discharge pump P4 in the actuators, providing real-time and accurate feedback on the pump status. The read operating status parameters are then displayed via a host computer HMI.

[0038] For pressure sensors, level sensors, and flow sensors, fault types include sensor hardware failure, signal interference, and data drift. For suction pump P1, suction pump P2, discharge pump P3, and discharge pump P4, fault types include abnormal motor temperature, abnormal inverter temperature, abnormal motor torque, abnormal speed, and abnormal bus voltage. After the acquisition module reads the operating status parameters of each pump and sensor, the data is displayed in list form on the host computer HMI, allowing operators to quickly obtain the real operating status of each pump in the sand mixing equipment system.

[0039] The fault detection method provided in this application involves a data acquisition module transmitting various operational status parameters to the control system via wired transmission for data analysis and processing. The host computer stores the operational status parameters of each pump or sensor, as well as fault information, in a database. The intelligent analysis function of the AI ​​fault diagnosis model mounted on the host computer is trained using deep learning algorithms based on historical fault data stored in the database. During model training, cross-validation is used to optimize model parameters, improving the model's accuracy in identifying different fault types.

[0040] After receiving various operating status parameters, the control system calls the edge computing layer of the AI ​​fault diagnosis model to preprocess the parameters, thereby filtering out abnormal data and marking it as suspected fault data. Then, the trained AI fault diagnosis model extracts features from the suspected fault data. In this embodiment, taking sensor faults as an example, feature extraction mainly focuses on extracting features such as the fluctuation frequency and abrupt change amplitude of the sensor data. These extracted features are then matched with fault features in the fault list to determine the corresponding fault type and output the corresponding fault diagnosis result. In addition to the determined fault type, the fault diagnosis result also displays the corresponding fault confidence level and the fault occurrence time, allowing operators to intuitively understand the specific fault situation and take appropriate preventative measures for potentially faulty sensors or perform maintenance on sensors that have already failed.

[0041] Meanwhile, the control system can periodically retrieve new fault data and diagnostic results from the database, thereby iteratively training the AI ​​fault diagnosis model and continuously improving its ability to identify new faults or faults in complex scenarios.

[0042] In a specific embodiment, when taking the motor failure of the pump body as an example, if the control system receives that the motor speed is increasing, but the suction pressure and flow rate are not increasing, the system will match the current working conditions with the preset working condition program in the program, and give several abnormal types that may cause the problem, so that the operator can make a judgment and repair.

[0043] In a specific embodiment, when the pressure sensor of the suction manifold is used as the embodiment, if the control system does not receive data from the pressure sensor of the suction manifold, but the flow rate and the speed of the pump motor are in an increasing state, the system will match the current working conditions with the preset working condition program in the program, and give several abnormal types that may cause the problem, so that the operator can make a judgment and repair.

[0044] In the embodiments provided in this application, when a fault occurs, the control system automatically switches to the corresponding operating mode based on the current operating conditions and the cause of the fault. This allows for rapid switching of the on / off state of the upper butterfly valve and the start / stop state of the pump, enabling switching between different operating modes. In different modes, the operating states of each butterfly valve are different, thereby switching the on / off state of each pipeline and the direction of liquid flow in the pipeline. In this embodiment, seven predefined operating modes are listed, and the correspondence between each predefined operating mode and each butterfly valve is shown in the following table:

[0045] During equipment operation, when a component malfunctions, the control system will automatically switch the butterfly valves, simultaneously controlling the suction pump P1, suction pump P2, discharge pump P3, discharge pump P4, flow control valve V15, and flow control valve V16 to achieve control of different fluid directions, thereby meeting operational process requirements and improving operational efficiency and reliability. The specific operating modes are as follows: Mode 0: In the custom mode, the opening and closing status of the corresponding butterfly valve will be entirely controlled manually by the operator on the host computer interface, thereby enabling flexible configuration and selection of fluid direction.

[0046] Mode 1: In this mode, independent sand adding operations can be achieved for both channels. One channel can operate independently, or both channels can operate simultaneously. During operation, sand adding can be selected to be either active or inactive. When this mode is selected, the corresponding butterfly valve will automatically open or close, creating the appropriate fluid flow path. If one of the channels malfunctions, the corresponding suction pump, flow control valve, and discharge pump can be shut down to prevent the malfunction from affecting the overall operation, while allowing the other channel to continue operating.

[0047] The flow directions of the fluid in the two pathways are as follows: First route: The liquid enters the mixing tank T1 through the suction pump P1 and flow control valve V15. The mixing tank T1 can be filled with the corresponding dry additives, liquid additives and proppant (usually fracturing sand). The liquid is then discharged to the downstream equipment through the discharge pump P4.

[0048] The second route: The liquid enters the mixing tank T2 through the suction pump P2 and the flow control valve V16. The mixing tank T2 can be filled with the corresponding dry additives, liquid additives and proppant (usually fracturing sand), and then discharged to the downstream equipment through the discharge pump P3.

[0049] In the above mode, the corresponding butterfly valve switching state is: Butterfly valves in the open position: V1, V3, V7, V9, V10, V12, V13, V14; Butterfly valves in the closed position: V2, V4, V5, V6, V8, V11; Mode 2: In this mode, only the first flow path can be used for sand addition. The second flow path can only be used for water dispensing, not sand addition. Both flow paths can be selected to operate or not operate as needed. After selecting this mode, the corresponding butterfly valve will automatically open or close, forming the appropriate fluid flow path. If one flow path malfunctions, the corresponding suction pump, flow control valve, and discharge pump can be shut down without affecting the operation of the other flow path.

[0050] The flow directions of the fluid in the two pathways are as follows: First route: The liquid enters the mixing tank T1 through the suction pump 1 and flow control valve V15, and is discharged to the downstream equipment through the discharge pump P4.

[0051] Second route: The liquid passes through the discharge pump P3, then through the flow sensor G3, and finally to the downstream equipment.

[0052] In this mode, the corresponding butterfly valve on / off state is: Butterfly valves in the open position: V1, V5, V7, V12, V13, V14; Butterfly valves in the closed position: V2, V3, V4, V6, V8, V9, V10, V11; Mode 3: In this mode, only the first flow path can be used for sand addition. The second flow path can only be used for water injection, not sand addition. Both flow paths can be selected to operate or not operate as needed. After selecting this mode, the corresponding butterfly valve will automatically open or close, forming the corresponding fluid flow path. If one flow path malfunctions, the corresponding suction pump, flow valve, and discharge pump can be shut down without affecting the operation of the other flow path.

[0053] The flow directions of the fluid in the two pathways are as follows: First route: The liquid enters the mixing tank T1 through the suction pump P1 and flow control valve V15, and is discharged to the downstream equipment through the discharge pump P4.

[0054] Second route: Liquid is pumped through suction pump P2 to downstream equipment.

[0055] In this mode, the corresponding butterfly valve on / off state is: Butterfly valves in the open position: V1, V4, V6, V12, V13, V14; Butterfly valves in the closed position: V2, V3, V5, V7, V8, V9, V10, V11; Mode 4: In this mode, only the first passage can perform sand adding operations. The second passage cannot perform sand adding operations; it can only perform water pumping operations. Both passages can be selected to operate or not operate as needed. After selecting this mode, the corresponding butterfly valve will automatically open or close, forming the corresponding fluid passage. If one passage malfunctions, the corresponding suction pump, flow valve, and discharge pump can be shut down without affecting the operation of the other passage.

[0056] The flow directions of the fluid in the two pathways are as follows: First route: The liquid enters the mixing tank T2 through the suction pump P1 and flow control valve V16, and is discharged to the downstream equipment through the discharge pump P3.

[0057] Second route: Liquid is pumped through suction pump P2 to downstream equipment.

[0058] In this mode, the corresponding butterfly valve on / off state is: Butterfly valves in the open position: V1, V2, V4, V6, V8, V9, V10; Butterfly valves in the closed position: V3, V5, V7, V11, V12, V13, V14; Mode 5: In this mode, only the first flow path can be used for sand addition. The second flow path can only be used for water dispensing, not sand addition. Both flow paths can be selected to operate or not operate as needed. After selecting this mode, the corresponding butterfly valve will automatically open or close, forming the appropriate fluid flow path. If one flow path malfunctions, the corresponding suction pump, flow valve, and discharge pump can be shut down without affecting the operation of the other flow path.

[0059] The flow directions of the fluid in the two pathways are as follows: First route: The liquid enters the mixing tank T2 through the suction pump P1 and flow control valve V16, and is discharged to the downstream equipment through the discharge pump P4.

[0060] Second route: The liquid is discharged via pump P3 to downstream equipment.

[0061] In this mode, the corresponding butterfly valve on / off state is: Butterfly valves in the open position: V1, V2, V5, V7, V10, V11, V13, V14; Butterfly valves in the closed position: V3, V4, V6, V8, V9, V12; Mode 6: In this mode, only the first flow path can be used for sand addition. The second flow path can only be used for water dispensing, not sand addition. Both flow paths can be selected to operate or not operate as needed. After selecting this mode, the corresponding butterfly valve will automatically open or close, forming the appropriate fluid flow path. If one flow path malfunctions, the corresponding suction pump, flow valve, and discharge pump can be shut down without affecting the operation of the other flow path.

[0062] The flow directions of the fluid in the two pathways are as follows: First route: The liquid enters the mixing tank T2 through the suction pump P1 and flow control valve V16, and is discharged to the downstream equipment through the discharge pump P4.

[0063] Second route: Liquid is pumped through suction pump P2 to downstream equipment.

[0064] In this mode, the corresponding butterfly valve on / off state is: Butterfly valves in the open position: V1, V2, V4, V6, V10, V11, V13, V14; Butterfly valves in the closed position: V3, V5, V7, V8, V9, V12; Mode 7: In this mode, only the first passage can perform sand adding operations. The second passage cannot perform sand adding operations; it can only perform water pumping operations. Both passages can be selected to operate or not operate as needed. After selecting this mode, the corresponding butterfly valve will automatically open or close, forming the corresponding fluid passage. If one passage malfunctions, the corresponding suction pump, flow valve, and discharge pump can be shut down without affecting the operation of the other passage.

[0065] The flow directions of the fluid in the two pathways are as follows: First route: The liquid enters the mixing tank T2 through the suction pump P1 and flow control valve V16, and is discharged to the downstream equipment through the discharge pump P3.

[0066] Second route: Liquid is pumped through suction pump P2 to downstream equipment.

[0067] Butterfly valves in the open position: V1, V2, V4, V6, V8, V9, V10; Butterfly valves in the closed state: V3, V5, V7, V11, V12, V13, V14.

[0068] Through the above methods, if a fault is detected or anticipated before or during on-site operations, the sand mixing equipment system can seamlessly switch between different operating modes based on the current operational status and the fault conditions of each executing or detecting component within the system. This fully meets the various needs of on-site operations. Furthermore, the intelligent control system design ensures the stability of the overall sand mixing equipment system's operation, reduces construction costs, and avoids downtime due to faults that could impact overall operational efficiency. This effectively improves construction efficiency, enhances the safety and reliability of on-site operations, and makes the well site more intelligent.

[0069] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0070] In the description of this application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0071] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0072] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "joining," and "fixing," etc., should be interpreted broadly. For example, they can refer to a connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0073] In this application, unless otherwise expressly specified and limited, "above" or "below" the second feature can include direct contact between the first and second features, or contact between the first and second features through another feature between them. Furthermore, "above," "over," and "on top" of the second feature includes the first feature being directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature includes the first feature being directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0074] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. The illustrative expressions of the above terms in this specification should not be construed as necessarily referring to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. In addition, those skilled in the art can combine and integrate the different embodiments or examples described in this specification.

[0075] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Since these modifications and variations fall within the scope of the claims and their equivalents, this application also intends to include these modifications and variations.

[0076] The above description describes specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A fault detection method for a sand mixing equipment, characterized in that, Includes the following steps: The control system reads the working status parameters of each actuator and detection component in the sand mixing equipment system; The control system calls the AI ​​fault diagnosis model to calculate and analyze the read working status parameters to determine whether there is a fault. If the AI ​​fault diagnosis model identifies and determines that there is a fault in the read working status parameters, it determines the fault feature in the fault list corresponding to the fault condition, and outputs the corresponding fault diagnosis result based on the determined fault feature. The control system receives the fault diagnosis results and adjusts the sand mixing equipment system accordingly, switching the working mode of the sand mixing equipment system pipeline.

2. The fault detection method for sand mixing equipment according to claim 1, characterized in that, After receiving the working status parameters, the host computer matches and binds the fault conditions judged by the AI ​​fault diagnosis model with the corresponding working status parameters, and stores them in the database as new fault data.

3. The fault detection method for sand mixing equipment according to claim 1, characterized in that, The AI ​​fault diagnosis model is trained through deep learning based on historical fault data in the database.

4. The fault detection method for sand mixing equipment according to claim 1, characterized in that, The specific steps of the AI ​​fault diagnosis model in identifying the received working status parameters are as follows: The working status parameters are compared and analyzed with the normal working parameters in the database, and data that differs from the normal working parameters are marked as suspected fault data. Feature extraction is performed on suspected fault data, and the extracted features are matched with the fault list to determine the fault characteristics; The fault diagnosis results are output based on the fault characteristics.

5. The fault detection method for sand mixing equipment according to claim 4, characterized in that, When extracting features from suspected faulty data, the extracted features include the data fluctuation frequency and the magnitude of sudden changes.

6. The fault detection method for sand mixing equipment according to claim 4, characterized in that, The fault diagnosis results include the fault type, fault confidence level, and fault occurrence time.

7. The fault detection method for sand mixing equipment according to claim 6, characterized in that, The fault types correspond to the fault characteristics in the fault list, and the fault types include: hardware abnormal faults, signal abnormal faults, and data abnormal faults.

8. The fault detection method for sand mixing equipment according to claim 1, characterized in that, The specific steps for the control system to adjust the sand mixing equipment system based on the fault diagnosis results are as follows: The on / off status of each pipeline in the sand mixing equipment system is switched by adjusting the flow conditions, and the faulty actuators or detection components are isolated, so that the pipelines bypass the faulty actuators or detection components to form new paths, thereby adjusting the working mode of the sand mixing equipment system pipelines.

Images