Fault diagnosis method for bridge crane

Abstract

The invention discloses a fault diagnosis method for a bridge crane, relates to the technical field of fault diagnosis, and solves the technical problem in the prior art that the operation of the bridge crane can be influenced by no consideration of environmental factors so as to cause crane faults. The method comprises the following steps: acquiring operation data of the bridge crane and surrounding environment data; calculating an environment early warning evaluation coefficient based on the environment data; judging whether early warning information is generated or not based on the environment early warning evaluation coefficient and a preset environment threshold value; if yes, early warning information is sent to the user side; if not, continuously monitoring and judging; training an artificial intelligence model based on the historical operation data and the corresponding environment data to obtain a fault recognition model; and performing fault prediction identification on the operation data of the bridge crane and the environment early warning evaluation coefficient corresponding to the environment data based on the fault identification model to obtain an identification result, thereby solving the technical problem.

Description

Technical Field

[0001] The invention belongs to the field of fault diagnosis, in particular to a fault diagnosis method for a bridge crane. Background Art

[0002] As an indispensable large-scale lifting equipment in industrial production, bridge cranes are prone to electrical system failures, mechanical component wear, control system failures, etc. due to the long-term heavy load, frequent start and stop, and harsh working environment. Traditional fault diagnosis methods mostly rely on manual inspections and experience judgments, which have shortcomings such as low efficiency, poor accuracy, and slow response, and are difficult to meet the high requirements of modern industrial production for equipment maintenance and management.

[0003] The prior art (the invention application with the publication number CN116281632A) discloses an intelligent hoisting control system for a factory bridge crane, including: a sensor perception module, a communication module, a control module and a management system module, wherein the management system module includes a control center and a cloud server, and the communication module is used to realize the communication between the sensor perception module and the edge side MCU, the communication between the edge side MCU and the control center, and the communication between the control center and the cloud server. This invention application is based on the multimodal characteristic parameters of the bridge crane body (mainly the trolley, the car, the lifting mechanism), the hoisting materials and the personnel collected by the industrial CCD image sensor, the displacement sensor, the vibration acceleration sensor, the noise sensor, and the current sensor, and uses the Internet of Things technology, semi-supervision and artificial intelligence prediction algorithms to effectively realize the prediction of bridge crane faults, reduce the mental labor of the staff, and ensure the safe and reliable operation of the bridge crane. However, the prior art does not take into account environmental factors, such as ambient temperature, ambient humidity and dust concentration, which can also affect the operation of the bridge crane, thereby causing the problem of crane failure.

[0004] Therefore, the present invention proposes a fault diagnosis method for a bridge crane to solve the above-mentioned problem. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a fault diagnosis method for a bridge crane, which is used to solve the technical problem that the prior art does not take into account environmental factors, such as ambient temperature, ambient humidity and dust concentration, which may also affect the operation of the bridge crane and cause crane failure.

[0006] To achieve the above object, a first aspect of the present invention provides a fault diagnosis method for a bridge crane, comprising:

[0007] Step 1: Obtain the operation data of the bridge crane and the surrounding environment data;

[0008] Step 2: Calculate the environmental warning assessment coefficient based on the environmental data; determine whether to generate warning information based on the environmental warning assessment coefficient and the preset environmental threshold; if yes, send the warning information to the user end; if no, continue to monitor and judge; wherein the user end includes: a mobile phone or a computer;

[0009] Step 3: Train the artificial intelligence model based on historical operation data and corresponding environmental data to obtain a fault identification model;

[0010] Step 4: Based on the fault identification model, the operating data of the bridge crane and the environmental warning assessment coefficient corresponding to the environmental data are used for fault prediction and identification to obtain the identification result.

[0011] Preferably, the obtaining of the operation data of the bridge crane and the surrounding environment data includes:

[0012] The data acquisition equipment is used to collect the operation data of the bridge crane and the surrounding environmental data in real time; the operation data and the environmental data correspond to the same collection time; the operation data include: vibration frequency, noise, current, voltage and displacement; the environmental data include: ambient temperature, ambient humidity and dust concentration.

[0013] It should be noted that the vibration frequency refers to the vibration generated by the key mechanical components of the crane (such as motors, bearings, gear boxes, drive shafts, etc.) during operation; noise sensors are placed near components that generate abnormal sounds, such as motors, gear boxes, etc.; current and voltage are collected on electrical equipment such as motors, frequency converters, power lines and control circuits; displacement data mainly includes the actual position and motion trajectory of the moving parts of the crane, including the lateral displacement of the trolley on the bridge, the longitudinal displacement of the trolley along the track, and the lifting and lowering displacement of the hook in the vertical direction.

[0014] Preferably, the environmental early warning assessment coefficient is calculated based on the environmental data, including:

[0015] The ambient temperature is marked as W, the ambient humidity is marked as H, and the dust concentration is marked as N;

[0016] Through the environmental early warning assessment coefficient formula:

[0017] P = A × e^[(W-ZW)^2 / (ZW)] + B × e^H / (e^H+1) + C × tanh(N) × ln(N), and the environmental early warning assessment coefficient is calculated; where P is the environmental early warning assessment coefficient, A, B, C are proportional coefficients, tanh(*) is the hyperbolic tangent function, and ln(*) is a logarithmic function with the natural number e as the base.

[0018] Preferably, the determining whether to generate warning information based on the environmental warning assessment coefficient and the preset environmental threshold value includes:

[0019] Determine whether the environmental warning assessment coefficient is greater than the preset environmental threshold; if yes, generate warning information; if not, continue to monitor and judge; among which, the preset environmental threshold is set according to the optimal environment under the actual normal operating state of the bridge crane.

[0020] Too high a temperature will affect the maintenance of the bridge crane and the heat of the outer surface, thus affecting its service life and lifting performance; high temperature may also cause changes in the material properties of certain components, such as aging of plastic parts and failure of lubricants; too low a temperature may harden the surface of the bridge crane, causing it to move slowly and clumsily during driving and lifting, affecting work efficiency; a humid environment can easily cause the metal parts of the bridge crane to rust, affecting its strength and stability. At the same time, humidity may also affect the normal operation of the crane's electronic instruments, wires, electrical appliances and other components, which may endanger life in severe cases; excessive dust may not only enter the mechanical equipment components inside the crane, damaging its application effect, but may also accelerate the damage of the equipment and even cause mechanical equipment damage;

[0021] The present invention collects environmental data around the bridge crane, calculates an environmental early warning assessment coefficient based on the environmental data, and determines whether to generate early warning information based on the environmental early warning assessment coefficient and a preset environmental threshold. This solves the problem that the prior art does not take into account that environmental factors will also affect the operation of the bridge crane, thereby causing crane failure.

[0022] Preferably, the training of the artificial intelligence model based on the historical operation data and the corresponding environmental data includes:

[0023] S1: The historical environmental warning assessment coefficient is calculated based on the environmental data at the time of collection of historical operation data using the environmental warning assessment coefficient formula;

[0024] S2: Matching the corresponding fault type through a database based on historical operation data and corresponding historical environmental warning assessment coefficients; wherein the database stores existing known crane fault types;

[0025] S3: Integrate historical operation data and corresponding historical environmental warning assessment coefficients into standard input data, and integrate corresponding fault types into standard output data;

[0026] S4: Train an artificial intelligence model based on standard input data and standard output data to obtain a fault identification model; wherein the artificial intelligence model includes: a convolutional neural network or a deep belief network.

[0027] It should be noted that the environmental data corresponding to the historical operating data at the time of collection refers to the real-time collection of the operating data of the bridge crane and the historical data of the surrounding environment data; the fault types include: motor failure, component overheating, abnormal displacement, bearing damage and gear wear, etc.

[0028] Preferably, the fault prediction and identification of the operating data of the bridge crane and the environmental warning assessment coefficient corresponding to the environmental data based on the fault identification model includes:

[0029] By inputting the operating data of the bridge crane and the environmental warning assessment coefficient corresponding to the environmental data into the fault identification model, an identification result is obtained; wherein the identification result refers to the fault type of the bridge crane.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] 1. The prior art does not take into account environmental factors, such as ambient temperature, ambient humidity and dust concentration, which may also affect the operation of the bridge crane, thereby causing the crane to malfunction. The present invention collects environmental data around the bridge crane, calculates an environmental early warning assessment coefficient based on the environmental data, and determines whether to generate early warning information based on the environmental early warning assessment coefficient and a preset environmental threshold, thereby solving the above problem.

[0032] 2. The present invention obtains a historical environmental warning assessment coefficient by calculating the environmental warning assessment coefficient formula based on the environmental data at the time of collection corresponding to the historical operating data; trains an artificial intelligence model based on the historical operating data and the corresponding historical environmental warning assessment coefficient to obtain a fault identification model; and performs fault prediction and identification on the operating data of the bridge crane and the environmental warning assessment coefficient corresponding to the environmental data based on the fault identification model to obtain an identification result, thereby solving the problem that the prior art does not take into account that environmental factors will also affect the operation of the bridge crane, resulting in a low accuracy rate in crane fault identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0034] Figure 1 A schematic diagram of the method steps of an embodiment of the present invention;

[0035] Figure 2 A schematic diagram of a specific process of an embodiment of the present invention;

[0036] Figure 3 Schematic diagram of environmental early warning assessment coefficient determination according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] See also Figure 1-Figure 2 The first embodiment of the present invention provides a fault diagnosis method for a bridge crane, comprising:

[0039] Step 1: Obtain the operation data of the bridge crane and the surrounding environment data;

[0040] Step 2: Calculate the environmental warning assessment coefficient based on the environmental data; determine whether to generate warning information based on the environmental warning assessment coefficient and the preset environmental threshold; if yes, send the warning information to the user end; if no, continue to monitor and judge; wherein the user end includes: a mobile phone or a computer;

[0041] Obtain the operating data of the bridge crane and the surrounding environment data, including:

[0042] The data acquisition equipment is used to collect the operation data of the bridge crane and the surrounding environmental data in real time; the operation data and the environmental data correspond to the same collection time; the operation data include: vibration frequency, noise, current, voltage and displacement; the environmental data include: ambient temperature, ambient humidity and dust concentration.

[0043] The environmental early warning assessment coefficient is calculated based on environmental data, including:

[0044] The ambient temperature is marked as W, the ambient humidity is marked as H, and the dust concentration is marked as N;

[0045] Through the environmental early warning assessment coefficient formula:

[0046] P = A × e^[(W-ZW)^2 / (ZW)] + B × e^H / (e^H+1) + C × tanh(N) × ln(N), and the environmental early warning assessment coefficient is calculated; where P is the environmental early warning assessment coefficient, A, B, C are proportional coefficients, tanh(*) is the hyperbolic tangent function, and ln(*) is a logarithmic function with the natural number e as the base.

[0047] See also Figure 3 , based on the environmental warning assessment coefficient and the preset environmental threshold, determine whether to generate warning information, including:

[0048] Determine whether the environmental warning assessment coefficient is greater than the preset environmental threshold; if yes, generate warning information; if not, continue to monitor and judge; among which, the preset environmental threshold is set according to the optimal environment under the actual normal operating state of the bridge crane.

[0049] For example, suppose that in a coal mine warehouse, a bridge crane is frequently lifting coal. Now it is necessary to perform real-time fault diagnosis on the crane, as follows:

[0050] 1. Data collection;

[0051] Data acquisition equipment:

[0052] Vibration sensors: Installed on key mechanical components such as crane motors, bearings and gearboxes to monitor vibration frequency in real time.

[0053] Noise sensor: Placed near the motor and gearbox to capture abnormal sounds.

[0054] Current and voltage monitors: Connect to motors, inverters, power lines and control circuits to record current and voltage data.

[0055] Displacement sensor: installed on the crane's trolley, carriage and hook to track their movement trajectory and position.

[0056] Environmental data collection: Integrate temperature sensors, humidity sensors and dust concentration sensors to comprehensively monitor the environment around the crane.

[0057] Collect data:

[0058] Ambient temperature (W): 30℃;

[0059] Ambient humidity (H): 60%;

[0060] Dust concentration (N): 500mg / m 3 ;

[0061] 2. Calculation of environmental early warning assessment coefficient;

[0062] Assume proportionality coefficients: A = 0.4, B = 0.5, C = 0.7;

[0063] Optimum ambient temperature (ZW): Assumed to be 25°C;

[0064] Calculate the environmental early warning assessment coefficient:

[0065] Through the environmental early warning assessment coefficient formula:

[0066] P = A × e^[(W-ZW)^2 / (ZW)] + B × e^H / (e^H+1) + C × tanh(N) × ln(N), calculate the environmental early warning assessment coefficient;

[0067] P=0.4×e^[(30-25)^2 / (25)]+0.5×e^60 / (e^60+1)+0.7×tanh(500)×ln(500)≈5.94;

[0068] 3. Early warning judgment;

[0069] Preset environmental threshold: Assume it is 5;

[0070] Judgment: Since the calculated environmental warning assessment coefficient of 5.94 is greater than the preset environmental threshold of 5, the system will generate a warning message.

[0071] 4. Send early warning information;

[0072] The system sends warning information to the operator's mobile phone and the computer in the factory monitoring center via the wireless network, reminding the operator that the crane needs to be inspected.

[0073] The present invention collects environmental data to calculate the environmental early warning assessment coefficient, monitors the operating environment of the bridge crane in real time, and generates early warning information when necessary to ensure the safe and stable operation of the crane. This method effectively solves the problem of ignoring the impact of environmental factors on crane operation in the prior art.

[0074] Step 3: Train the artificial intelligence model based on historical operation data and corresponding environmental data to obtain a fault identification model;

[0075] Step 4: Based on the fault identification model, the operating data of the bridge crane and the environmental warning assessment coefficient corresponding to the environmental data are used for fault prediction and identification to obtain the identification result.

[0076] Training artificial intelligence models based on historical operating data and corresponding environmental data, including:

[0077] S1: The historical environmental warning assessment coefficient is calculated based on the environmental data at the time of collection of historical operation data using the environmental warning assessment coefficient formula;

[0078] S2: Matching the corresponding fault type through a database based on historical operation data and corresponding historical environmental warning assessment coefficients; wherein the database stores existing known crane fault types;

[0079] S3: Integrate historical operation data and corresponding historical environmental warning assessment coefficients into standard input data, and integrate corresponding fault types into standard output data;

[0080] S4: Train an artificial intelligence model based on standard input data and standard output data to obtain a fault identification model; wherein the artificial intelligence model includes: a convolutional neural network or a deep belief network.

[0081] Based on the fault identification model, the operating data of the bridge crane and the environmental warning assessment coefficient corresponding to the environmental data are used to predict and identify faults, including:

[0082] By inputting the operating data of the bridge crane and the environmental warning assessment coefficient corresponding to the environmental data into the fault identification model, an identification result is obtained; wherein the identification result refers to the fault type of the bridge crane.

[0083] For example, it is necessary to perform fault prediction and identification on a bridge crane, as follows:

[0084] 1. Data collection and preprocessing;

[0085] Historical operation data and environmental data collection:

[0086] Use the data acquisition system to continuously record the operating data of each crane in the past year, including vibration frequency, noise, current, voltage, displacement, etc.

[0087] At the same time, the environmental data corresponding to the collection time is recorded, including: ambient temperature, humidity and dust concentration.

[0088] 2. Calculation of environmental early warning assessment coefficient;

[0089] For each set of historical operating data collected and its corresponding environmental data, the historical environmental early warning assessment coefficient is calculated using the environmental early warning assessment coefficient formula.

[0090] For example, the environmental data recorded at one time is: temperature 32°C, humidity 80%, dust concentration 300mg / m 3 The corresponding environmental early warning assessment coefficient is calculated through the formula.

[0091] Matching fault type:

[0092] Based on historical operating data and historical environmental warning evaluation coefficients, historical fault information is matched from the database, including fault types (such as motor failure, component overheating, abnormal displacement, bearing damage, gear wear, etc.) and maintenance measures.

[0093] 3. Artificial intelligence model training;

[0094] Data Integration:

[0095] The historical operating data (such as vibration frequency, current, etc.) and the corresponding historical environmental warning assessment coefficients are integrated into standard input data.

[0096] The corresponding fault types (such as motor failure, bearing damage, etc.) are integrated into standard output data.

[0097] Model training:

[0098] The integrated standard input data and standard output data are used as training sets to train the CNN model.

[0099] By continuously adjusting the network structure, optimizer settings and hyperparameters, the model's performance on the training set (such as accuracy, recall rate, etc.) is optimized.

[0100] 4. Fault prediction and identification;

[0101] Real-time data input:

[0102] When the crane is running, its operating data and environmental data are collected in real time, and the current environmental warning assessment coefficient is calculated.

[0103] Failure prediction:

[0104] The real-time operation data and its corresponding environmental warning assessment coefficients are input into the trained CNN model.

[0105] The model outputs the possible failure types of the current crane.

[0106] For example, suppose that at a certain point in time, the real-time operation data of the crane shows that the vibration frequency is abnormally high, and the environmental data shows that the dust concentration reaches 400mg / m 3 , the environmental warning assessment coefficient calculated by the environmental warning assessment coefficient formula also exceeds the threshold.

[0107] After inputting this data into the CNN model, the model output showed "bearing damage".

[0108] The maintenance personnel obtain corresponding maintenance measures based on the fault type of "bearing damage" to handle the crane.

[0109] The present invention improves the accuracy of bridge crane fault identification and reduces downtime and maintenance costs caused by faults by training an artificial intelligence model based on historical operation data and its corresponding environmental data, and using the model to perform fault prediction and identification.

[0110] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0111] Working principle of the present invention:

[0112] The present invention obtains the operating data of the bridge crane and the surrounding environmental data; calculates the environmental early warning evaluation coefficient based on the environmental data; determines whether to generate early warning information based on the environmental early warning evaluation coefficient and the preset environmental threshold; if yes, sends the early warning information to the user end; if not, continuously monitors and determines; trains an artificial intelligence model based on the historical operating data and the corresponding environmental data to obtain a fault identification model; performs fault prediction and identification on the operating data of the bridge crane and the environmental early warning evaluation coefficient corresponding to the environmental data based on the fault identification model to obtain an identification result, thereby solving the problem that the prior art does not take into account that environmental factors will also affect the operation of the bridge crane, thereby causing crane failure.

[0113] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A fault diagnosis method for a bridge crane, characterized in that: include: Step 1: Obtain the operation data of the bridge crane and the surrounding environment data; Step 2: Calculate the environmental warning assessment coefficient based on environmental data; Determine whether to generate warning information based on the environmental warning assessment coefficient and the preset environmental threshold; If yes, a warning message is sent to the user end; If not, continue to monitor and judge; the user end includes: mobile phone or computer; Step 3: Train the artificial intelligence model based on historical operation data and corresponding environmental data to obtain a fault identification model; Step 4: Based on the fault identification model, the operating data of the bridge crane and the environmental warning assessment coefficient corresponding to the environmental data are used to perform fault prediction and identification to obtain the identification result.

2. A method for diagnosing a fault of a bridge crane according to claim 1, characterized in that: The obtaining of the operation data of the bridge crane and the surrounding environment data includes: The data acquisition equipment is used to collect the operation data of the bridge crane and the surrounding environmental data in real time; the operation data and the environmental data correspond to the same collection time; the operation data include: vibration frequency, noise, current, voltage and displacement; the environmental data include: ambient temperature, ambient humidity and dust concentration.

3. A fault diagnosis method for a bridge crane according to claim 1, characterized in that: The environmental early warning assessment coefficient is calculated based on environmental data, including: The ambient temperature is marked as W, the ambient humidity is marked as H, and the dust concentration is marked as N; Through the environmental early warning assessment coefficient formula: P = A × e^[(W-ZW)^2 / (ZW)] + B × e^H / (e^H+1) + C × tanh(N) × ln(N), and the environmental early warning assessment coefficient is calculated; where P is the environmental early warning assessment coefficient, A, B, C are proportional coefficients, tanh(*) is the hyperbolic tangent function, and ln(*) is a logarithmic function with the natural number e as the base.

4. A method for diagnosing a fault of a bridge crane according to claim 1, characterized in that: The determining whether to generate warning information based on the environmental warning assessment coefficient and the preset environmental threshold value includes: Determine whether the environmental warning assessment coefficient is greater than the preset environmental threshold; if yes, generate warning information; if not, continue to monitor and judge; among which, the preset environmental threshold is set according to the optimal environment under the actual normal operating state of the bridge crane.

5. A method for diagnosing a fault of a bridge crane according to claim 1, characterized in that: The training of the artificial intelligence model based on the historical operation data and the corresponding environmental data includes: S1: The historical environmental warning assessment coefficient is calculated based on the environmental data at the time of collection of historical operation data using the environmental warning assessment coefficient formula; S2: Matching the corresponding fault type through a database based on historical operation data and corresponding historical environmental warning assessment coefficients; wherein the database stores existing known crane fault types; S3: Integrate historical operation data and corresponding historical environmental warning assessment coefficients into standard input data, and integrate corresponding fault types into standard output data; S4: Train an artificial intelligence model based on standard input data and standard output data to obtain a fault identification model; wherein the artificial intelligence model includes: a convolutional neural network or a deep belief network.

6. A method for diagnosing a fault of a bridge crane according to claim 1, characterized in that: The method of performing fault prediction and identification on the operating data of the bridge crane and the environmental early warning assessment coefficient corresponding to the environmental data based on the fault identification model includes: By inputting the operating data of the bridge crane and the environmental warning assessment coefficient corresponding to the environmental data into the fault identification model, an identification result is obtained; wherein the identification result refers to the fault type of the bridge crane.

Images