A method and system for handling loading equipment failures

Abstract

This invention provides a method and system for handling loading equipment faults, relating to the field of equipment fault early warning and response technology. By collecting status data during the operation of the loading equipment, extracting fault characteristics, and performing fault identification, this invention can capture early, weak fault symptoms, thus proactively providing early warnings before the fault escalates and promptly addressing early faults, achieving proactive maintenance. Secondly, by selecting a target response level from multiple preset response levels based on the target fault probability, and selecting a target response strategy from multiple preset response strategies based on the target fault type and target response level, this hierarchical fault response mechanism enables the invention to achieve a balance between ensuring production safety and operational efficiency.

Description

Technical Field

[0001] This invention relates to the field of equipment fault early warning and response technology, specifically to a method and system for handling faults in loading equipment. Background Technology

[0002] Currently, bulk material loading stations, such as those for coal, ore, and grain, have widely deployed loading equipment including telescopic chutes, frequency conversion winches, coal feeders, belt conveyors, hydraulic gates, coal levelers, static track scales, and traction mechanisms.

[0003] In existing technologies, fault detection of loading equipment relies on manual inspection and built-in single-point protection, such as integrated protection devices for coal feeders and belt pull rope switches. Upon detecting a fault, a binary response mode of shutdown or no response is executed, such as direct shutdown when the belt deviates.

[0004] However, existing technologies have some shortcomings: First, because they can only trigger protection against extreme faults such as overload and over-temperature, they can only detect amplified faults, making operation and maintenance passive. Second, the "one-size-fits-all" binary response mode is difficult to balance production safety and operational efficiency. For example, when the belt deviates slightly, a direct shutdown will affect the continuity of loading operations. Summary of the Invention

[0005] In view of this, in order to solve the above-mentioned technical problems, the present invention provides a method and system for handling vehicle loading equipment failures.

[0006] The present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a method for handling malfunctions of loading equipment, comprising: Collect status data during the operation of loading equipment; Perform data preprocessing on the state data to obtain preprocessed state data; Fault features are extracted from the preprocessed state data to obtain fault features; Based on the fault characteristics, fault identification is performed to obtain identification results; when the loading equipment has a fault, the identification results include the target fault type and the target fault probability. For each target fault type, a target response level is selected from a plurality of preset response levels based on the corresponding target fault probability; When the target response level is not zero, a target response strategy is selected from a plurality of preset response strategies based on the target fault type and the target response level. Execute the target response strategy.

[0008] Optionally, the response levels include level zero, level one, level two, and level three; The failure probability range corresponding to level zero is less than 30%; The failure probability range corresponding to Level 1 is greater than or equal to 30% and less than 60%; The failure probability range corresponding to the second level is greater than or equal to 60% and less than 85%; The failure probability range corresponding to the third level is greater than or equal to 85%.

[0009] Optionally, based on the fault characteristics, fault identification is performed, specifically including: For each preset fault type, calculate the similarity between the preset fault features and the preset fault features; Determine whether there is a target similarity greater than a preset similarity threshold among all the aforementioned similarities; If among all the similarities, there is a target similarity greater than a preset similarity threshold, then the preset fault type corresponding to the target similarity is determined as the target fault type.

[0010] Optionally, based on the fault characteristics, fault identification may further include: Using a backpropagation neural network, the target fault probability corresponding to the target fault type is calculated based on the fault characteristics.

[0011] Optionally, after executing the target response strategy, this method further includes: After the maintenance personnel have handled the fault and obtained the corresponding fault handling data, they optimize the preset fault features and / or the backpropagation neural network based on the fault handling data.

[0012] Optionally, the state data may undergo data preprocessing, specifically including: The state data is denoised using a Gaussian filtering algorithm.

[0013] Optionally, the loading equipment includes power transmission equipment, traction and actuation equipment, control and auxiliary equipment, and metering and testing equipment; The power transmission equipment includes a belt conveyor and a coal feeder; The traction and execution equipment includes a frequency conversion winch, a traction mechanism, and a telescopic chute; The control and auxiliary equipment includes hydraulic gates, coal levelers, buffer silo level sensors, and environmental adaptation equipment; the environmental adaptation equipment includes anti-fog equipment and dust removal equipment. The measurement and testing equipment includes a static track scale and a lidar.

[0014] Optionally, the status data of the belt conveyor includes belt misalignment distance data, idler vibration data, motor current, motor temperature, and pull rope switch status; The status data of the coal feeder includes motor current, motor temperature, bearing temperature, gate switch status, and material level matching data. The status data of the variable frequency winch includes bearing temperature, bearing vibration data, drum vibration data, braking current, and traction speed. The status data of the traction mechanism includes hook clearance and traction force; The status data of the telescopic chute includes vibration data of the hydraulic drive mechanism, pressure of the hydraulic system, material level data of the metering bin, and lifting displacement. The status data of the hydraulic gate includes the temperature of the outer wall of the cylinder, the gate opening degree, the gate opening and closing time, and data related to cylinder leakage. The status data of the coal leveler includes data related to the lifting mechanism jamming, displacement data, displacement sensor malfunction data, and material surface flatness feedback anomaly data. The status data of the buffer silo level sensor includes signal distortion-related data and level data; The status data of the anti-fog device includes motor current; The status data of the dust removal equipment includes motor current; The status data of the static track scale includes weighing data, sensor fault-related data, and signal transmission anomaly-related data. The status data of the lidar includes scanning anomaly related data, signal interruption related data, and data distortion related data.

[0015] Secondly, the present invention provides a vehicle loading equipment fault handling system, comprising: The data acquisition module is used to collect status data during the operation of the loading equipment. The preprocessing module is used to perform data preprocessing operations on the state data to obtain preprocessed state data; The extraction module is used to extract fault features from the preprocessed state data to obtain fault features; The identification module is used to identify faults based on the fault characteristics and obtain identification results; when the loading equipment has a fault, the identification results include the target fault type and the target fault probability. The first selection module is used to select a target response level from a plurality of preset response levels for each target fault type, based on the corresponding target fault probability. The second selection module is used to select a target response strategy from a plurality of preset response strategies based on the target fault type and the target response level when the target response level is not zero. The execution module is used to execute the target response strategy.

[0016] This invention employs the above technical solution to provide a method for handling faults in loading equipment, comprising: collecting status data during the operation of the loading equipment; performing data preprocessing on the status data to obtain preprocessed status data; extracting fault features from the preprocessed status data to obtain fault features; performing fault identification based on the fault features to obtain identification results; when a fault exists in the loading equipment, the identification results include a target fault type and a target fault probability; for each target fault type, selecting a target response level from a set of preset response levels based on the corresponding target fault probability; when the target response level is not zero, selecting a target response strategy from a set of preset response strategies based on the target fault type and the target response level; and executing the target response strategy.

[0017] Based on this, by collecting status data during the operation of the loading equipment, extracting fault characteristics, and performing fault identification, this invention can capture early, weak fault signs of the equipment, thus proactively issuing warnings before the fault escalates and promptly addressing early faults, achieving proactive operation and maintenance. Secondly, by selecting a target response level from multiple preset response levels based on the target fault probability, and selecting a target response strategy from multiple preset response strategies based on the target fault type and target response level, this hierarchical fault response mechanism enables this invention to achieve a balance between ensuring production safety and operational efficiency. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating a method for handling vehicle loading equipment malfunctions according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a vehicle loading equipment fault handling system provided in an embodiment of the present invention; Figure 3 This is the embodiment of the invention corresponding to Figure 2 The overall architecture and equipment integration diagram of the loading equipment fault handling system. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be described in detail below. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other implementation methods obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0021] Figure 1 This is a flowchart illustrating a method for handling loading equipment malfunctions according to an embodiment of the present invention. This method is adaptable to various intelligent upgrade scenarios for bulk material loading stations in the field of intelligent loading on railways without fixed warehousing units. For example... Figure 1 As shown, this method includes: Step 101: Collect status data during the operation of the loading equipment.

[0022] Specifically, the loading equipment may include power transmission equipment, traction and actuation equipment, control and auxiliary equipment, and metering and testing equipment.

[0023] Power transmission equipment includes belt conveyors and coal feeders.

[0024] The traction and actuation equipment includes frequency conversion winches, traction mechanisms, and telescopic chutes.

[0025] Control and auxiliary equipment includes hydraulic gates, coal levelers, buffer silo level sensors, and environmental adaptation equipment; environmental adaptation equipment includes anti-fog equipment and dust removal equipment.

[0026] Measurement and testing equipment includes static track scales and lidar.

[0027] The status data of the belt conveyor may include belt misalignment distance data, idler vibration data, motor current, motor temperature, and pull rope switch status.

[0028] The status data of the coal feeder includes motor current, motor temperature, bearing temperature, gate switch status, and material level matching related data. Material level matching related data refers to the data used to analyze whether there are any abnormalities in material level matching in the coal feeder. This material level matching related data is existing technology and will not be elaborated upon here.

[0029] The status data of the variable frequency winch includes bearing temperature, bearing vibration data, drum vibration data, braking current, and traction speed. It should be noted that the vibration data in this invention are all obtained using triaxial vibration sensors.

[0030] The status data of the traction mechanism includes hook clearance and traction force.

[0031] The status data of the telescopic chute includes vibration data of the hydraulic drive mechanism, pressure of the hydraulic system, material level data of the metering bin, and lifting displacement.

[0032] The status data of the hydraulic gate includes the temperature of the cylinder outer wall, the gate opening degree, the gate opening and closing time, and data related to cylinder leakage. Similarly, the data related to cylinder leakage refers to the data used in analyzing whether there is cylinder leakage in the hydraulic gate, which is existing technology and will not be described in detail here.

[0033] The status data of the coal leveler includes data related to lifting mechanism jamming, displacement data, displacement sensor malfunction data, and data related to abnormal material surface leveling feedback. Similarly, the lifting mechanism jamming data refers to data used when analyzing whether the coal leveler has a jammed lifting mechanism; the displacement sensor malfunction data refers to data used when analyzing whether the coal leveler has a malfunctioning displacement sensor; and the material surface leveling feedback abnormality data refers to data used when analyzing whether the coal leveler has abnormal material surface leveling feedback. These three are all existing technologies, and will not be elaborated upon here.

[0034] The status data of the buffer silo level sensor includes signal distortion correlation data and level data. Signal distortion correlation data refers to the data used when analyzing whether there is signal distortion in the buffer silo level sensor, which is existing technology and will not be described in detail here.

[0035] The status data of anti-fog equipment includes motor current. Specifically, anti-fog equipment can be an anti-fog fan.

[0036] The status data of the dust removal equipment includes motor current.

[0037] The status data of a static rail scale includes weighing data, sensor fault-related data, and signal transmission anomaly-related data. Sensor fault-related data refers to data used when analyzing whether a sensor fault exists in the static rail scale; signal transmission anomaly-related data refers to data used when analyzing whether a signal transmission anomaly exists in the static rail scale. Both of these are existing technologies and will not be elaborated upon here.

[0038] The status data of a lidar includes scanning anomaly-related data, signal interruption-related data, and data distortion-related data. Scanning anomaly-related data is used to analyze whether the lidar exhibits scanning anomalies; signal interruption-related data is used to analyze whether the lidar experiences signal interruptions; and data distortion-related data is used to analyze whether the lidar exhibits data distortion. These three are all existing technologies and will not be elaborated upon here. Furthermore, the lidar can be a 2D lidar or a 3D lidar.

[0039] In addition, since the status data includes both data collected by the new sensors and the operating data of the existing equipment, the collection frequency of the status data can be set to 100 Hz in order to ensure that the data collected by the new sensors is synchronized with the operating data of the existing equipment in time and space.

[0040] Step 102: Perform data preprocessing on the state data to obtain preprocessed state data.

[0041] Specifically, data preprocessing operations on the state data can include: A Gaussian filtering algorithm is used to denoise the state data, specifically removing data noise caused by dust and temperature and humidity fluctuations, thereby improving data validity.

[0042] Step 103: Extract fault features from the preprocessed state data to obtain fault features.

[0043] Specifically, parameters such as the motor current fluctuation coefficient of the coal feeder, the root mean square value of the bearing vibration of the variable frequency winch, the belt misalignment distance, the pressure change rate of the hydraulic system of the telescopic chute, the temperature rise rate of each motor, the gate opening and closing time deviation of the hydraulic gate, and the displacement deviation of the leveler can be extracted. Then, a standardized feature vector, i.e., fault characteristics, can be generated. In this way, the present invention can be compatible with the fault characteristic patterns of various loading equipment.

[0044] Among them, motor current fluctuation coefficient The extraction formula is as follows: ......(1) In the formula, The standard deviation of the motor current; This represents the average value of the motor current.

[0045] exist If the value exceeds a preset threshold, it is considered abnormal. The preset threshold can be 0.2, and can be fine-tuned later based on actual conditions, such as the device model.

[0046] Root mean square value of vibration The extraction formula is as follows: ......(2) In the formula, when calculating the frequency converter winch... hour, This refers to the bearing vibration amplitude of the variable frequency winch; in calculating the belt conveyor... hour, This refers to the vibration amplitude of the idler rollers of the belt conveyor. This represents the number of vibration amplitude samples collected.

[0047] exist If the value exceeds a preset root mean square threshold, it is considered abnormal. The preset root mean square threshold can be 0.3g, enabling this invention to be adapted to fault identification of various rotating components.

[0048] Step 104: Based on the fault characteristics, perform fault identification and obtain the identification results. When the loading equipment has a fault, the identification results include the target fault type and the target fault probability. Conversely, when the loading equipment does not have a fault, the identification results do not include the target fault type and the target fault probability.

[0049] Specifically, fault identification is performed based on fault characteristics, which may include: (1) For each preset fault type, calculate the similarity between the preset fault features and the preset fault features. The preset fault types may include overload of the coal feeder motor, belt misalignment, and abnormal braking of the variable frequency winch. The preset fault features of all preset fault types can be stored in the fault feature library. Preset fault features include, for example: normal operating current range of coal feeder 30 to 50A, normal vibration amplitude of variable frequency winch bearing ≤0.3g, and safe threshold for belt misalignment distance ≤50mm. This invention supports fine-tuning of parameter thresholds according to different loading station operating conditions.

[0050] (2) Determine whether there is a target similarity greater than the preset similarity threshold among all similarities. The preset similarity threshold can be 0.8.

[0051] (3) If there is a target similarity greater than the preset similarity threshold among all similarities, then the preset fault type corresponding to the target similarity is determined as the target fault type.

[0052] Furthermore, based on fault characteristics, fault identification may also include: Using a BP (Backpropagation) neural network, the target fault probability corresponding to the target fault type is calculated based on the fault characteristics.

[0053] Specifically, to improve fault identification speed and meet the real-time loading process requirements of various loading stations, this invention employs a lightweight BP neural network. "Lightweight" here refers to its relatively simple network structure. For example, a lightweight BP neural network includes one input layer, one or two hidden layers, and one output layer. The identification time of this lightweight BP neural network is less than or equal to 100ms. In a specific example, assuming the aforementioned fault feature dimension is 12, the input layer can have 12 neurons, corresponding to the 12 input feature dimensions; the hidden layer can be set to one layer containing 8 neurons; and the output layer can have 3 neurons, corresponding to the probabilities of the three states: "normal," "potential fault," and "serious fault." Finally, the BP neural network outputs the probability of taking the highest value. Thus, the fault probability is used to measure the severity of the corresponding fault type.

[0054] It should be noted that the BP neural network is trained using a large number of fault samples corresponding to preset fault types, for example, more than 500 sets of fault samples. Furthermore, the training method for the BP neural network is existing technology, and will not be elaborated upon here.

[0055] Step 105: For each target fault type, select the target response level from multiple preset response levels based on the corresponding target fault probability.

[0056] In a specific example, the response levels include Level 0, Level 1, Level 2, and Level 3.

[0057] The failure probability range corresponding to level zero is less than 30%.

[0058] The failure probability range corresponding to Level 1 is greater than or equal to 30% and less than 60%.

[0059] The failure probability range corresponding to Level 2 is greater than or equal to 60% and less than 85%.

[0060] The failure probability range corresponding to Level 3 is greater than or equal to 85%.

[0061] Step 106: When the target response level is not zero, select the target response strategy from multiple preset response strategies based on the target fault type and the target response level.

[0062] Specifically, this invention pre-defines response strategies corresponding to each response level for each fault type. Therefore, after determining the target fault type and target response level, the target response strategy can be selected based on this correspondence.

[0063] In a specific example, the target fault type is feeder motor overload, and the target response level is Level 1. In this case, there is no immediate safety risk; therefore, the corresponding response strategy can be: generate and display preset warning information, such as a pop-up warning on the intelligent loading management platform. Secondly, fault data can be recorded, and standardized handling suggestions can be pushed, such as checking if the feeder gate is blocked. Furthermore, without interrupting the current loading operation, existing PLCs can be linked to adjust equipment operating parameters, such as reducing the feeder speed, to slow the fault's progression and ensure process continuity. Subsequently, the current fault condition is continuously monitored; once the fault is alleviated, the current loading status is maintained; however, if the fault escalates, the next level of response strategy is implemented.

[0064] In addition, when the target fault type is a decrease in hydraulic system pressure of the telescopic chute or a fluctuation in motor current of the coal feeder, and the target response level is Level 1, a similar response strategy can be adopted, since neither of them poses an immediate safety risk.

[0065] In another specific example, the target fault type is belt misalignment, and the target response level is level two. This situation can affect loading quality or equipment lifespan. Therefore, the corresponding response strategy could be: generating and displaying preset alarm information, such as activating audible and visual alarms, with alarm tones differentiated by the faulty equipment area. Secondly, it could suspend operations on the branch line where the faulty equipment is located and switch to backup equipment, such as activating a backup hydraulic pump. Furthermore, it could link with the existing loading planning system to skip the affected sections of the carriages, maintaining the overall loading process. Finally, it could automatically generate a fault report, which could include equipment type, fault characteristics, and standardized handling steps to facilitate accurate handling by maintenance personnel. Subsequently, after the maintenance personnel have handled the issue, the original loading status is restored. Simultaneously, the corresponding fault handling data is acquired, and the preset fault features and / or backpropagation neural network are optimized based on this data.

[0066] In addition, when the target fault type is a blockage in the coal leveler lifting mechanism, a jamming of the coal feeder gate, or abnormal vibration of the frequency converter winch, and the target response level is level two, a similar response strategy can be adopted, because they will all affect the loading quality or equipment life.

[0067] In another specific example, the target fault type is abnormal variable frequency winch braking, and the target response level is level three. This situation poses a safety hazard; therefore, the corresponding response strategy could be: immediately trigger an emergency shutdown to cut off the power to the faulty equipment. Secondly, the existing PLC centralized control system can be linked to suspend the entire loading operation. Furthermore, standardized safety protection mechanisms can be activated to prevent the fault from escalating and causing a safety accident or significant material loss. Subsequently, after the fault is resolved, the system is restarted to resume loading.

[0068] In addition, when the target fault type is belt misalignment, hydraulic system pressure drop in telescopic chute, or coal feeder motor overload, and the target response level is level three, a similar response strategy can be adopted as described above, because all of them pose safety hazards.

[0069] Through the above-mentioned graded fault response strategy, this invention can avoid unplanned downtime and ensure production safety under common faults such as slight belt misalignment, slight overload of coal feeder motor and slight jamming of coal leveler lifting mechanism. At the same time, it can also stop and repair in the event of safety hazards, thus ensuring production safety under various conditions and possessing strong engineering versatility and applicability.

[0070] Step 107: Execute the target response strategy.

[0071] This invention employs the aforementioned technical solution. By collecting various status data during the operation of the loading equipment, extracting fault characteristics, and performing fault identification, this invention can capture early, weak fault signs, thus proactively issuing warnings before the fault escalates and promptly addressing early faults, achieving proactive maintenance. Secondly, by selecting a target response level from multiple preset response levels based on the target fault probability, and selecting a target response strategy from multiple preset response strategies based on the target fault type and target response level, this hierarchical fault response mechanism enables the invention to achieve a balance between ensuring production safety and operational efficiency.

[0072] Furthermore, when the target response level is zero, step 101: collecting status data during the operation of the loading equipment is re-executed. Also, after executing the target response strategy, step 101: collecting status data during the operation of the loading equipment is also re-executed. That is, in practical application, the method process of this invention is continuously repeated to achieve continuous fault handling of the loading equipment.

[0073] In this embodiment of the invention, after executing the target response strategy, the vehicle loading equipment fault handling method of the present invention may further include: After the maintenance personnel have handled the fault and obtained the corresponding fault handling data, they optimize the preset fault features and / or the backpropagation neural network based on the fault handling data.

[0074] As mentioned above, when the target fault type is belt misalignment or other fault types, and the target response level is level two, a fault report can be generated, allowing maintenance personnel to accurately handle the fault based on the report. This invention acquires fault handling data based on the maintenance personnel's actions and adds it to a preset fault sample database. Subsequently, using the fault handling data in the preset fault sample database, an incremental learning algorithm is used to optimize preset fault features and / or backpropagation neural networks. This enables the invention to continuously improve the accuracy of early warnings and its adaptability to specific loading station operating conditions, forming a closed-loop system of "collection-identification-response-optimization," and providing long-term adaptability to the needs of aging loading station equipment and changing operating conditions.

[0075] The core formula of the incremental learning algorithm is as follows: ......(3) In the formula, These are the updated model parameters; These are the model parameters before the update; Training parameters for newly added fault samples; These are the weighting coefficients. .

[0076] In this way, the present invention can take into account both the stability of historical parameters and the adaptability to new faults and new working conditions, with an update time of ≤500ms, and without affecting the normal loading operation of the loading station.

[0077] Based on a general inventive concept, the present invention also provides a vehicle loading equipment fault handling system. Figure 2 This is a schematic diagram of a vehicle loading equipment fault handling system provided in an embodiment of the present invention. Figure 2 As shown, this system includes: The data acquisition module 21 is used to collect status data during the operation of the loading equipment.

[0078] The preprocessing module 22 is used to perform data preprocessing operations on the state data to obtain preprocessed state data.

[0079] Extraction module 23 is used to extract fault features from the preprocessed state data to obtain fault features.

[0080] The identification module 24 is used to identify faults based on fault characteristics and obtain identification results. When there is a fault in the loading equipment, the identification results include the target fault type and the target fault probability.

[0081] The first selection module 25 is used to select a target response level from a plurality of preset response levels for each target fault type based on the corresponding target fault probability.

[0082] The second selection module 26 is used to select a target response strategy from a plurality of preset response strategies based on the target fault type and the target response level when the target response level is not zero.

[0083] Execution module 27 is used to execute the target response strategy.

[0084] Optionally, response levels may include level zero, level one, level two, and level three.

[0085] The failure probability range corresponding to level zero is less than 30%.

[0086] The failure probability range corresponding to Level 1 is greater than or equal to 30% and less than 60%.

[0087] The failure probability range corresponding to Level 2 is greater than or equal to 60% and less than 85%.

[0088] The failure probability range corresponding to Level 3 is greater than or equal to 85%.

[0089] Optionally, the recognition module 24 can be used for: For each preset fault type, calculate the similarity between the preset fault features and the preset fault features.

[0090] Determine whether there is a target similarity greater than a preset similarity threshold among all similarities.

[0091] If among all similarities, there exists a target similarity greater than the preset similarity threshold, then the preset fault type corresponding to the target similarity is determined as the target fault type.

[0092] Optionally, the recognition module 24 can also be used for: Using a backpropagation neural network, the target fault probability corresponding to the target fault type is calculated based on the fault characteristics.

[0093] Optionally, this system may also include an optimization module for: After the target response strategy is executed and the maintenance personnel have handled the fault and obtained the corresponding fault handling data, the preset fault features and / or backpropagation neural network are optimized based on the fault handling data.

[0094] Optional, preprocessing module 22 can be used for: A Gaussian filtering algorithm is used to denoise the state data.

[0095] Optionally, the loading equipment includes power transmission equipment, traction and actuation equipment, control and auxiliary equipment, and metering and testing equipment.

[0096] Power transmission equipment includes belt conveyors and coal feeders.

[0097] The traction and actuation equipment includes frequency conversion winches, traction mechanisms, and telescopic chutes.

[0098] Control and auxiliary equipment includes hydraulic gates, coal levelers, buffer silo level sensors, and environmental adaptation equipment; environmental adaptation equipment includes anti-fog equipment and dust removal equipment.

[0099] Measurement and testing equipment includes static track scales and lidar.

[0100] Optionally, the status data of the belt conveyor includes belt misalignment distance data, idler vibration data, motor current, motor temperature, and pull rope switch status.

[0101] The status data of the coal feeder includes motor current, motor temperature, bearing temperature, gate switch status, and material level matching data.

[0102] The status data of the variable frequency winch includes bearing temperature, bearing vibration data, drum vibration data, braking current, and traction speed.

[0103] The status data of the traction mechanism includes hook clearance and traction force.

[0104] The status data of the telescopic chute includes vibration data of the hydraulic drive mechanism, pressure of the hydraulic system, material level data of the metering bin, and lifting displacement.

[0105] The status data of the hydraulic gate includes the temperature of the outer wall of the cylinder, the gate opening degree, the gate opening and closing time, and data related to cylinder leakage.

[0106] The status data of the coal leveler includes data related to the lifting mechanism jamming, displacement data, displacement sensor malfunction data, and abnormal material surface leveling feedback data.

[0107] The status data of the buffer silo level sensor includes signal distortion-related data and level data.

[0108] The status data of the anti-fog equipment includes motor current.

[0109] The status data of the dust removal equipment includes motor current.

[0110] The status data of a static rail scale includes weighing data, sensor fault-related data, and signal transmission anomaly-related data.

[0111] The status data of lidar includes data related to scanning anomalies, data related to signal interruptions, and data related to data distortion.

[0112] Figure 3 This is the embodiment of the invention corresponding to Figure 2 The overall architecture and equipment integration diagram of the loading equipment fault handling system. (See diagram below.) Figure 3As shown, the acquisition module 21 includes a current sensor, a temperature sensor, a vibration sensor, a working condition related sensor, and a data synchronization acquisition unit.

[0113] Among them, the current sensor can collect current data from components such as the motor of the coal feeder and the motor of the belt conveyor. The current sensor has a measurement range of 0 to 500A and an accuracy of ±0.5%. Specifically, it is used to collect the motor operating current, peak current and fluctuation frequency. It is standardized and deployed in the motor control circuit of the power distribution room and is compatible with AC / DC motors.

[0114] The temperature sensor can be an infrared temperature sensor with a measurement range of -20℃ to 200℃ and an accuracy of ±0.3℃. It can collect temperature data from key heat-generating components such as the motor windings of coal feeders, the bearings of variable frequency winches, and the outer wall of hydraulic gate cylinders. The temperature sensor can be fixed magnetically or with bolts to adapt to different equipment structures.

[0115] The vibration sensor can be a triaxial vibration sensor with a measurement range of 0.1 to 100 Hz and an accuracy of ±0.01g. It can collect vibration data from the hydraulic drive mechanisms of variable frequency winch drums, belt conveyor idlers, and telescopic chutes. The vibration sensor has an IP65 protection rating to adapt to complex working conditions such as dust and humidity.

[0116] Operating condition-related sensors can include pressure sensors, distance sensors, level gauges, and humidity sensors. Pressure sensors can collect pressure data from the hydraulic system of telescopic chutes, with a measurement range of 0 to 31.5 MPa, and use a universal threaded interface. Distance sensors can collect data on belt misalignment distances of belt conveyors, with an accuracy of ±1 mm, and use an adjustable mounting bracket structure. Level gauges can be ultrasonic level gauges, which can collect relevant material level data. Humidity sensors can collect ambient humidity data.

[0117] The data synchronization acquisition unit synchronously acquires data from the current sensor, temperature sensor, vibration sensor, and operating condition correlation sensor, as well as relevant data collected by the original data acquisition device of the loading equipment, to obtain the aforementioned status data of the loading equipment during operation. The data synchronization acquisition unit can be integrated into the existing remote I / O module of the loading station, is compatible with mainstream industrial communication protocols such as Profinet and Modbus, and has an acquisition frequency of 100Hz to ensure that the acquired data is synchronized with the loading conditions in time and space, thus adapting to different brands of PLC (Programmable Logic Controller) systems. It should be noted that the current sensor, temperature sensor, vibration sensor, operating condition correlation sensor, and data synchronization acquisition unit are new hardware structures added in this application compared to existing technologies.

[0118] The preprocessing module 22, extraction module 23, identification module 24, first selection module 25, and second selection module 26 all rely on a computing device. Specifically, the computing device is an edge computing device, which can be deployed next to the PLC cabinet in the power distribution room of the loading station. Equipped with an industrial-grade AI chip, this invention can improve data processing speed and support millisecond-level data processing.

[0119] The execution module 27 depends on the computing device and the PLC. Specifically, the computing device generates control commands based on the target response strategy and sends them to the PLC. The PLC responds to the control commands and controls the corresponding equipment to operate, for example, controlling the operation of the existing emergency stop button, audible and visual alarm device and / or hydraulic gate at the loading station.

[0120] In addition, this system may also include an interactive client. The interactive client can be embedded into the intelligent loading management platform of the loading station, adding fault warning pop-ups and a tiered response operation interface, supporting maintenance personnel to view real-time data and fine-tune compensation parameters, such as vibration thresholds and temperature alarm limits, to adapt to the operation logic of different management platforms.

[0121] In addition, a mobile alert app can be designed, supporting mainstream operating systems (iOS / Android), capable of receiving and pushing real-time information on the type, location, and risk level of device malfunctions, as well as standardized handling suggestions generated by the system. This app supports remote confirmation and execution of preset response actions to adapt to mobile work scenarios for maintenance personnel.

[0122] In summary, this invention is seamlessly compatible with existing PLC centralized control systems and intelligent loading management platforms at loading stations. It deeply links fault data with the loading process, thereby enabling dynamic adjustment of work plans based on the scope of fault impact. It has high adaptability and balances versatility and practicality.

[0123] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0124] It should be noted that in the description of this invention, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this invention, unless otherwise stated, "a plurality of" means at least two.

[0125] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0126] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0127] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0128] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0129] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0130] In the description of this specification, 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 the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer 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.

[0131] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for handling faults in loading equipment, characterized in that, include: Collect status data during the operation of loading equipment; Perform data preprocessing on the state data to obtain preprocessed state data; Fault features are extracted from the preprocessed state data to obtain fault features; Based on the aforementioned fault characteristics, fault identification is performed, and identification results are obtained; When the loading equipment malfunctions, the identification result includes the target fault type and the target fault probability; For each target fault type, a target response level is selected from a plurality of preset response levels based on the corresponding target fault probability; When the target response level is not zero, a target response strategy is selected from a plurality of preset response strategies based on the target fault type and the target response level. Execute the target response strategy.

2. The method for handling loading equipment malfunctions according to claim 1, characterized in that, The response levels include Level 0, Level 1, Level 2, and Level 3; The failure probability range corresponding to level zero is less than 30%; The failure probability range corresponding to Level 1 is greater than or equal to 30% and less than 60%; The failure probability range corresponding to the second level is greater than or equal to 60% and less than 85%; The failure probability range corresponding to the third level is greater than or equal to 85%.

3. The method for handling loading equipment malfunctions according to claim 1, characterized in that, Based on the aforementioned fault characteristics, fault identification is performed, specifically including: For each preset fault type, calculate the similarity between the preset fault features and the preset fault features; Determine whether there is a target similarity greater than a preset similarity threshold among all the aforementioned similarities; If among all the similarities, there is a target similarity greater than a preset similarity threshold, then the preset fault type corresponding to the target similarity is determined as the target fault type.

4. The method for handling loading equipment malfunctions according to claim 3, characterized in that, Based on the aforementioned fault characteristics, fault identification is performed, which specifically includes: Using a backpropagation neural network, the target fault probability corresponding to the target fault type is calculated based on the fault characteristics.

5. The method for handling loading equipment malfunctions according to claim 4, characterized in that, After executing the target response strategy, the following is also included: After the maintenance personnel have handled the fault and obtained the corresponding fault handling data, they optimize the preset fault features and / or the backpropagation neural network based on the fault handling data.

6. The method for handling loading equipment malfunctions according to claim 1, characterized in that, The state data undergoes data preprocessing operations, specifically including: The state data is denoised using a Gaussian filtering algorithm.

7. The method for handling loading equipment malfunctions according to claim 1, characterized in that, The loading equipment includes power transmission equipment, traction and execution equipment, control and auxiliary equipment, and metering and testing equipment; The power transmission equipment includes a belt conveyor and a coal feeder; The traction and execution equipment includes a frequency conversion winch, a traction mechanism, and a telescopic chute; The control and auxiliary equipment includes hydraulic gates, coal levelers, buffer silo level sensors, and environmental adaptation equipment; the environmental adaptation equipment includes anti-fog equipment and dust removal equipment. The measurement and testing equipment includes a static track scale and a lidar.

8. The method for handling loading equipment malfunctions according to claim 7, characterized in that, The status data of the belt conveyor includes belt misalignment distance data, idler vibration data, motor current, motor temperature, and pull rope switch status; The status data of the coal feeder includes motor current, motor temperature, bearing temperature, gate switch status, and material level matching data. The status data of the variable frequency winch includes bearing temperature, bearing vibration data, drum vibration data, braking current, and traction speed. The status data of the traction mechanism includes hook clearance and traction force; The status data of the telescopic chute includes vibration data of the hydraulic drive mechanism, pressure of the hydraulic system, material level data of the metering bin, and lifting displacement. The status data of the hydraulic gate includes the temperature of the outer wall of the cylinder, the gate opening degree, the gate opening and closing time, and data related to cylinder leakage. The status data of the coal leveler includes data related to the lifting mechanism jamming, displacement data, displacement sensor malfunction data, and material surface flatness feedback anomaly data. The status data of the buffer silo level sensor includes signal distortion-related data and level data; The status data of the anti-fog device includes motor current; The status data of the dust removal equipment includes motor current; The status data of the static track scale includes weighing data, sensor fault-related data, and signal transmission anomaly-related data. The status data of the lidar includes scanning anomaly related data, signal interruption related data, and data distortion related data.

9. A fault handling system for loading equipment, characterized in that, include: The data acquisition module is used to collect status data during the operation of the loading equipment. The preprocessing module is used to perform data preprocessing operations on the state data to obtain preprocessed state data; The extraction module is used to extract fault features from the preprocessed state data to obtain fault features; The identification module is used to identify faults based on the fault characteristics and obtain identification results. When the loading equipment malfunctions, the identification result includes the target fault type and the target fault probability; The first selection module is used to select a target response level from a plurality of preset response levels for each target fault type, based on the corresponding target fault probability. The second selection module is used to select a target response strategy from a plurality of preset response strategies based on the target fault type and the target response level when the target response level is not zero. The execution module is used to execute the target response strategy.

Images