Tower crane fault self-diagnosis method and system based on multi-source information fusion analysis

Abstract

The invention discloses a tower crane fault self-diagnosis method and system based on multi-source information fusion analysis. The method comprises the following steps: (1) measuring and processing information; (2) extracting data features; (3) comparing and identifying; (4) fault diagnosis and trend prediction; and (5) fault reporting and early warning. The change of the operation state of the tower crane is detected in real time by utilizing equipment such as a sensor, an encoder, a limiter, a voltage meter, an ampere meter and a PLC, description of the operation and relative static states of the tower crane is enhanced through acquisition of multi-source signals, meanwhile, a cloud data knowledge base is extended to be used for simulating a tower crane model, and the simulation efficiency is improved. Therefore, the fault diagnosis can be realized more quickly and accurately. Meanwhile, by means of a data mining neural network algorithm, the algorithm is continuously trained and optimized, and the weight is adjusted, so that the future trend of the tower crane fault is obtained, prediction of the tower crane fault is facilitated, the working efficiency of the tower crane is improved, and the service life of the tower crane is prolonged.

Description

Technical Field

[0001] The invention relates to a tower crane fault self-diagnosis method and system based on multi-source information fusion analysis, belonging to the technical field of tower crane fault diagnosis. Background Art

[0002] The research background of tower crane fault self-diagnosis mainly comes from the following aspects:

[0003] First, safety needs: Tower cranes are indispensable and important construction machinery in fields such as construction. They have various functions, including lifting and handling, and are widely used around the world. However, due to the complex structure of tower cranes and the harsh working environment, tower cranes are prone to various failures in actual operations, which seriously affect the construction progress and worker safety. Traditional fault diagnosis methods mainly rely on manual inspections and experience judgment, which are inefficient and prone to errors.

[0004] The second is the consideration of economic benefits: tower crane fault self-diagnosis technology can detect and handle faults in a timely manner, avoid equipment shutdown and maintenance due to faults, reduce maintenance costs and time, and improve work efficiency.

[0005] The third is the promotion of technological development: With the development of modern science and technology, especially the continuous progress of sensor technology, computer technology, signal processing technology, etc., strong technical support has been provided for tower crane fault self-diagnosis. These technologies make it possible to conduct real-time monitoring and data analysis of the tower crane's operating status, thereby improving the accuracy and reliability of fault self-diagnosis.

[0006] At present, the domestic tower crane industry does not generally use an integrated fault self-diagnosis system to perform accurate fault diagnosis and fault analysis and prediction on tower cranes. The existing scheme discloses a tower crane fault diagnosis system (CN111158307A), including a PC controller, a PLC controller, a cloud server, a working condition information acquisition sensor and a tower crane operation information acquisition sensor, wherein the working condition information acquisition sensor and the tower crane operation information acquisition sensor are connected to the PLC controller, the PLC controller is connected to the cloud server through a wireless communication module, and the PLC controller is connected to the cloud server through the TCP / IP protocol; at the same time, a model corresponding to the tower crane is built into the cloud server; when working, the cloud server inputs the working condition information parameters into the corresponding tower crane model for simulation, and obtains the corresponding simulated operation parameters, and by comparing the simulated operation parameters with the actual operation parameters, the working state of the tower crane is determined and the corresponding diagnosis results are sent to the PC terminal and the operator of the specific PLC controller, thereby realizing real-time monitoring of the working state of the tower crane.

[0007] The above solution has the following problems:

[0008] 1) Only the failure problems that may occur during the operation of the tower crane are considered, and the impact of factors such as wind impact that may occur when the tower crane is in a relatively static state is not considered.

[0009] 2) The electric control part of the tower crane is the nerve center of the tower crane and the most important part of the tower crane actuator. Its performance and quality are related to the performance and brand of a tower crane, and even determine the life safety of related personnel. According to statistics, 70% of the failures in the operation of the tower crane are caused by the electric control system. Therefore, it is very necessary to analyze the failure of electrical equipment. The existing scheme only detects the working parameters of the tower crane (weight, height, angle, amplitude), and does not pay attention to the failure of the metal structure and power equipment of the tower crane. Summary of the invention

[0010] In view of the problems existing in the above-mentioned prior art, the present invention provides a tower crane fault self-diagnosis method and system based on multi-source information fusion analysis.

[0011] In order to achieve the above object, the present invention adopts a tower crane fault self-diagnosis method based on multi-source information fusion analysis, comprising the following steps:

[0012] (1) Information acquisition and processing: When the tower crane is in a relatively static condition and during operation, the detection device installed at the set position of the tower crane is used to perform real-time detection of the tower crane to obtain detection information;

[0013] (2) Data feature extraction: The detection information of step (1) is used as the reference value, and the data features are obtained by converting the analog quantity or digital quantity into the physical quantity, taking the tower body foundation as the origin, and determining the rotation zero position. The data features are then calibrated and uploaded to the cloud database in real time for the establishment of the tower crane operation data model;

[0014] (3) Comparison and identification: Compare the data features of step (2) with the historical status of the equipment and the tower crane operation data model established in the cloud database to identify whether there is an abnormality or fault, and then issue an abnormality or fault alarm signal;

[0015] (4) Fault diagnosis and trend prediction: Based on the identification results of step (3), combined with the structural characteristics and working principle of the tower crane, the fault is further judged and located;

[0016] (5) Fault reporting and early warning: Generate detailed fault reports and issue corresponding early warning signals according to the fault level.

[0017] As an improvement, in step (1), the spatial position of the boom frame, the angle change of each movement and the speed information are measured by a height sensor installed on the boom and an angle sensor and a rotary encoder installed on the rotary mechanism.

[0018] As an improvement, in step (1), the temporal and spatial position of the hook is identified by an amplitude sensor installed on the amplitude variation mechanism, a gun camera and a pan / tilt camera that follow the hook in real time, and the relative position change of the front and rear action states is obtained, and the structural stress information is measured by a stress patch sensor.

[0019] As an improvement, in step (2), the mutual conversion between analog quantity or digital quantity and physical quantity includes:

[0020] For the encoder, input the digital AD value into the PLC, and through the calibration operation, make different AD values ​​correspond to different positions of tower height, arm length, and rotation angle;

[0021] For the potentiometer, the analog quantity is input into the PLC, and through calibration operations, different voltage and current values ​​are made to correspond one by one with different positions of tower height, arm length, and rotation angle.

[0022] As an improvement, the abnormality or fault in step (3) includes: abnormal stress, abnormal speed, abnormal position, and abnormal lifting performance.

[0023] As an improvement, in step (4), the specific fault type and location are diagnosed in combination with the historical status and operation records of the tower crane to obtain a fault code model tree.

[0024] As an improvement, the fault report in step (5) includes fault cause, location and severity information.

[0025] The second aspect of the present invention further provides a tower crane fault self-diagnosis system based on multi-source information fusion analysis, which is used to implement the tower crane fault self-diagnosis method based on multi-source information fusion analysis, comprising:

[0026] The information acquisition and processing module is used to detect the tower crane in real time and obtain detection information by using sensors and encoders installed at set positions of the tower crane under relatively static conditions and during operation of the tower crane;

[0027] The data feature extraction module is used to use the detection information of the information measurement and processing module as the reference value, convert analog or digital quantities into physical quantities, take the tower body foundation as the origin, determine the rotation zero position, perform calibration operations, obtain data features, and upload them to the cloud database in real time for the establishment of the tower crane operation data model;

[0028] A data feature extraction module is used to compare the data features of the data feature extraction module with the historical status of the equipment and the tower crane operation data model established by the cloud database to identify whether there is an abnormality or fault, and then issue an abnormality or fault alarm signal;

[0029] The fault diagnosis and trend module is used to further judge and locate the fault according to the recognition results of the data feature extraction module and the structural characteristics and working principle of the tower crane;

[0030] The fault reporting and warning module is used to generate detailed fault reports and send out corresponding warning signals according to the fault level.

[0031] As an improvement, a tower crane operation model based on machine learning and data mining techniques relying on neural network algorithms is also included.

[0032] As an improvement, it also includes a display control terminal for displaying fault information and inputting control instructions.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] (1) High efficiency. The tower crane driver only needs to check the fault problem self-diagnosed by the tower crane in the display control terminal (touch screen), and then handle the fault problem according to the fault knowledge base provided by it to solve the tower crane fault. Compared with regular manual inspections, it saves labor costs and improves efficiency.

[0035] (2) High accuracy and safety. Relatively speaking, the tower crane fault self-diagnosis system uses a cloud data knowledge base to compare and identify faults, which is more accurate than manual inspections that rely more on personal experience. At the same time, manual inspections are bound to make mistakes, and the present invention only needs to regularly check and maintain the cloud database to greatly improve the accuracy and safety of the work.

[0036] (3) Simple and clear, easy to operate. The present invention is integrated into the display control terminal equipped with the intelligent housekeeper system, fully considering the human-computer interaction, and realizing the visualization of tower crane fault problems during fault detection and diagnosis. Whether it is the display of the fault problem, the sound and light alarm, or the fault solution, it will be displayed on the display screen, which is simple and convenient to operate. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application 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 application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0038] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0039] In order to make the objectives, technical solutions and advantages of the present invention more clear, the technical solutions of the present application are described in detail below with the help of accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solutions of the present application, rather than limitations on the technical solutions of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0040] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0041] Example 1

[0042] like Figure 1 As shown, a tower crane fault self-diagnosis method based on multi-source information fusion analysis includes the following steps:

[0043] (1) Information acquisition and processing: When the tower crane is in a relatively static condition and in operation, the detection device installed at the set position of the tower crane is used, including a height sensor installed on the boom, an angle sensor installed on the slewing mechanism, and a slewing encoder to measure the spatial position of the boom frame, the angle change and speed of each movement, and the amplitude sensor installed on the luffing mechanism, the gun camera and the pan / tilt camera that follow the hook in real time to identify the spatiotemporal position of the hook and obtain the relative position change of the previous and next action states. The stress patch sensor is used to measure the structural stress and other information to obtain the detection information;

[0044] (2) Data feature extraction: The detection information of step (1) is used as the reference value, and the data features are obtained by converting the analog quantity or digital quantity into the physical quantity, taking the tower body foundation as the origin, and determining the rotation zero position. The data features are then calibrated and uploaded to the cloud database in real time for the establishment of the tower crane operation data model;

[0045] It should be noted that the mutual conversion between analog or digital quantities and physical quantities includes: for encoders, inputting digital AD values ​​into PLC, and making different AD values ​​correspond to different positions of tower height, arm length, and rotation angle through calibration operations; for potentiometers, inputting analog quantities into PLC, and making different voltage and current values ​​correspond to different positions of tower height, arm length, and rotation angle through calibration operations;

[0046] (3) Comparison and identification: Compare the data features of step (2) with the historical status of the equipment (the status read in real time before each action of the tower crane) and the tower crane operation data model established in the cloud database, and judge whether there is internal hidden damage by whether there is abnormal stress, whether there is abnormal speed (overspeed), abnormal position (hook hitting the top, limit), abnormal lifting performance (overload, over torque) and other phenomena to monitor the real-time operation status of the electronic control part, and then identify and issue abnormal or fault alarm signals;

[0047] (4) Fault diagnosis and trend prediction: Based on the identification results of step (3), combined with the structural characteristics and working principle of the tower crane, the fault is further judged and located;

[0048] ① Combined with the historical status and operation records of the tower crane, the specific fault type and location can be diagnosed, and a partial fault code model tree as shown in Table 1 below can be obtained;

[0049] Table 1 Partial fault code model tree

[0050]

[0051]

[0052] (5) Fault reporting and early warning: Generate detailed fault reports and issue corresponding early warning signals according to the fault level; as shown in Table 2 below;

[0053] Table 2 Over 80% torque fault warning logic

[0054]

[0055] Taking Table 2 as an example, when a torque limit fault exceeding 80% occurs, the controller controls the lifting and lowering limits to three gears; the amplitude change is limited to one gear outward and unlimited inward; the indicator light Y31 flashes continuously at intervals of 1s (0.5S on, 0.5S off).

[0056] The present invention utilizes sensors, encoders, limiters, voltage and current meters, PLC and other equipment to detect changes in the operating state of the tower crane in real time. The working parameter information (weight, torque, height, angle, amplitude) of the tower crane is collected by sensors and encoders installed in corresponding mechanisms. The weight and torque sensors are located at the arm root of the boom jib and are used to detect the tonnage and lifting torque of the tower crane; the height sensor and the lifting encoder are located at the lifting mechanism, and the lifting height is determined by the length of the wire rope retracted and released by the lifting mechanism; the angle sensor is generally used for boom-type tower cranes and is used to detect the pitch angle of the boom of the boom tower crane; the rotary encoder is located at the rotary mechanism and is used to detect the rotary angle; the amplitude sensor and the variable amplitude encoder are located at the rotary mechanism and are used to detect the rotary angle. The device is located in the luffing mechanism and is used to detect the moving distance of the luffing trolley. The real-time voltage and current are collected by the electrical measuring instruments connected to the circuit. The digital and analog quantities entered by the above devices are transmitted to the PLC for subsequent processing. After the calibration operation, the PLC will correspond different AD values ​​to different positions of tower height, arm length, and rotation angle, and obtain the correct and reliable real-time position and status based on the real-time AD value provided by the above detection equipment. If the AD value fed back by the detection equipment exceeds the limit, the controller will provide different diagnostic results according to the results of the over-limit of different devices and issue control instructions to the protection device to execute corresponding protection operations such as shutdown of the lifting, rotation, luffing and other mechanisms or sound and light warning for the tower crane.

[0057] Example 2

[0058] A tower crane fault self-diagnosis system based on multi-source information fusion analysis, used to implement the tower crane fault self-diagnosis method based on multi-source information fusion analysis described in Example 1, comprising:

[0059] The information acquisition and processing module is used to detect the tower crane in real time and obtain detection information by using sensors and encoders installed at set positions of the tower crane under relatively static conditions and during operation of the tower crane;

[0060] The data feature extraction module is used to use the detection information of the information measurement and processing module as the reference value, convert analog or digital quantities into physical quantities, take the tower body foundation as the origin, determine the rotation zero position, perform calibration operations, obtain data features, and upload them to the cloud database in real time for the establishment of the tower crane operation data model;

[0061] A data feature extraction module is used to compare the data features of the data feature extraction module with the historical status of the equipment and the tower crane operation data model established by the cloud database to identify whether there is an abnormality or fault, and then issue an abnormality or fault alarm signal;

[0062] The fault diagnosis and trend module is used to further judge and locate the fault according to the recognition results of the data feature extraction module and the structural characteristics and working principle of the tower crane;

[0063] The fault reporting and warning module is used to generate detailed fault reports and send out corresponding warning signals according to the fault level.

[0064] The information acquisition and processing module is based on installing vibration, lifting weight and torque sensors at the root of the tower crane boom to detect changes in the boom metal structure, load weight and lifting torque when the boom is subjected to torque; installing vibration sensors on the part of the tower crane body close to the ground to detect the impact of the tower body on the tower base when it is subjected to unbalanced torque; installing speed sensors and pressure sensors on the tower crane's luffing trolley to ensure the smooth operation of the trolley mechanism; installing height, angle, amplitude sensors and encoders in the lifting, slewing and luffing mechanisms to collect real-time working parameters of the tower crane; in addition, installing power measuring instruments in the main control cabinets of various power equipment (such as motors, frequency converters, etc.) in the electric control system to confirm the working conditions of power equipment such as motors and frequency converters;

[0065] The multi-source information data of the information acquisition and processing module is converted into comparable digital quantities through PLC, and the cloud database inputs these operating information parameters into the physical model of the tower crane of the same model for simulation, and obtains the corresponding simulated operating parameters, which are compared with the characteristic information extracted from the actual operating tower crane. The cloud database stores relevant knowledge about the cause of the fault. During the detection process, PLC collects the fault information of the target equipment in real time, and comprehensively uses the experience in the fault library to track the fault tree fault code to identify the fault, so as to achieve the purpose of finding the type and location of the fault, obtain the specific corresponding fault situation, and make corresponding fault feedback decisions.

[0066] In addition, the present invention also adds a tower crane operation model that relies on machine learning and data mining technology based on neural network algorithms in the entire system. Neural network technology is developed by imitating the characteristics of human brain neural networks. It has the characteristics of parallel processing, self-organization, self-learning and nonlinear mapping. The most basic neuron characteristic function is:

[0067] y i =F(∑w i x j +s i );

[0068] In the formula, y i is the output function; F is the characteristic function; x1, x2, …x j , used to represent multiple input signals; w1, w2, …w i , represents the weighted value of each input signal; s i It is feedback information.

[0069] Neural network technology is used to extract useful information from a large amount of operating data for fault diagnosis. Neural network, support vector machine and other algorithms are used to learn historical data. Each signal is weighted and analyzed according to the importance of its impact on the model. During the training process, the node weights are adjusted according to the output values ​​through a continuous feedback process to establish a prediction model. Ultimately, the weights of possible future faults are determined, thereby identifying future fault trends.

[0070] The present invention uses sensors, encoders, limiters, voltage, current meters, PLC and other equipment to detect changes in the operating state of the tower crane in real time. Through the collection of multi-source signals, the description of the tower crane's operation and relative static state is enhanced. At the same time, the cloud data knowledge base is extended to simulate the tower crane model in order to achieve faster and more accurate fault diagnosis. At the same time, with the help of data mining neural network algorithms, the optimization algorithm is continuously trained and the weights are adjusted to obtain the future trend of tower crane failures, which is convenient for predicting tower crane failures, improving tower crane work efficiency, and extending the service life of tower cranes. Finally, the present invention is integrated into a display control terminal equipped with an intelligent housekeeper system, fully considering human-computer interaction, and realizing the visualization of tower crane failure problems during fault detection and diagnosis.

[0071] In addition, those skilled in the art will understand that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments also means being within the scope of protection of the present invention and forming different embodiments. For example, in the above embodiments, those skilled in the art can use them in combination according to the known technical solutions and the technical problems to be solved by this application.

Claims

1. A tower crane fault self-diagnosis method based on multi-source information fusion analysis, characterized in that: The following steps are involved: (1) Information acquisition and processing: When the tower crane is in a relatively static condition and during operation, the detection device installed at the set position of the tower crane is used to perform real-time detection of the tower crane to obtain detection information; (2) Data feature extraction: The detection information of step (1) is used as the reference value, and the data features are obtained by converting the analog quantity or digital quantity into the physical quantity, taking the tower body foundation as the origin, and determining the rotation zero position. The data features are then calibrated and uploaded to the cloud database in real time for the establishment of the tower crane operation data model; (3) Comparison and identification: Compare the data features of step (2) with the historical status of the equipment and the tower crane operation data model established in the cloud database to identify whether there is an abnormality or fault, and then issue an abnormality or fault alarm signal; (4) Fault diagnosis and trend prediction: Based on the identification results of step (3), combined with the structural characteristics and working principle of the tower crane, the fault is further judged and located; (5) Fault reporting and early warning: Generate detailed fault reports and issue corresponding early warning signals based on the fault level.

2. A tower crane fault self-diagnosis method based on multi-source information fusion analysis according to claim 1, characterized in that: In the step (1), the spatial position of the boom frame, the angle change of each movement and the speed information are measured by a height sensor installed on the boom and an angle sensor and a rotary encoder installed on the rotary mechanism.

3. A tower crane fault self-diagnosis method based on multi-source information fusion analysis according to claim 1 or 2, characterized in that: In the step (1), the temporal and spatial position of the hook is identified by the amplitude sensor installed on the amplitude variation mechanism, the gun camera and the pan / tilt camera that follow the hook in real time, and the relative position change of the front and rear action states is obtained, and the structural stress information is measured by the stress patch sensor.

4. The tower crane fault self-diagnosis method based on multi-source information fusion analysis according to claim 1 is characterized in that: In the step (2), the mutual conversion between analog quantity or digital quantity and physical quantity includes: For the encoder, the digital AD value is input into the PLC, and the different AD values ​​are made to correspond to the tower height, arm length, and different positions of the rotation angle through calibration operation; For the potentiometer, the analog quantity is input into the PLC, and through calibration operation, different voltage and current values ​​are made to correspond one by one with different positions of tower height, arm length, and rotation angle.

5. The tower crane fault self-diagnosis method based on multi-source information fusion analysis according to claim 1 is characterized in that: The abnormality or failure in step (3) includes: abnormal stress, abnormal speed, abnormal position, and abnormal lifting performance.

6. The tower crane fault self-diagnosis method based on multi-source information fusion analysis according to claim 1 is characterized in that: In the step (4), the specific fault type and location are diagnosed based on the historical status and operation records of the tower crane to obtain a fault code model tree.

7. The tower crane fault self-diagnosis method based on multi-source information fusion analysis according to claim 1 is characterized in that: The fault report in step (5) includes the fault cause, location and severity information.

8. A tower crane fault self-diagnosis system based on multi-source information fusion analysis, characterized in that: The tower crane fault self-diagnosis method based on multi-source information fusion analysis for implementing any one of claims 1 to 7 comprises: The information acquisition and processing module is used to detect the tower crane in real time and obtain detection information by using sensors and encoders installed at set positions of the tower crane under relatively static conditions and during operation of the tower crane; The data feature extraction module is used to use the detection information of the information measurement and processing module as the reference value, convert analog or digital quantities into physical quantities, take the tower body foundation as the origin, determine the rotation zero position, perform calibration operations, obtain data features, and upload them to the cloud database in real time for the establishment of the tower crane operation data model; A data feature extraction module is used to compare the data features of the data feature extraction module with the historical status of the equipment and the tower crane operation data model established by the cloud database to identify whether there is an abnormality or fault, and then issue an abnormality or fault alarm signal; The fault diagnosis and trend module is used to further judge and locate the fault according to the recognition results of the data feature extraction module and the structural characteristics and working principle of the tower crane; The fault reporting and warning module is used to generate detailed fault reports and send out corresponding warning signals according to the fault level.

9. A tower crane fault self-diagnosis system based on multi-source information fusion analysis according to claim 8, characterized in that: It also includes a tower crane operation model that relies on machine learning and data mining techniques using neural network algorithms.

10. A tower crane fault self-diagnosis system based on multi-source information fusion analysis according to claim 8 or 9, characterized in that: It also includes a display control terminal for displaying fault information and inputting control instructions.

Images