Search

CN-121978973-A - Transient instability identification and self-adaptive damping control method and system for hoisting equipment

CN121978973ACN 121978973 ACN121978973 ACN 121978973ACN-121978973-A

Abstract

The invention discloses a method and a system for transient instability identification and self-adaptive damping control of hoisting equipment, which relate to the technical field of intelligent control of hoisting equipment and comprise the following steps of collecting equipment inclination, vibration, load and other data in a multi-dimensional manner and preprocessing the data; extracting core characteristic parameters, eliminating redundant information, identifying transient instability risks and judging grades through a neural network model, calculating optimal damping control parameters according to the risk grades and working conditions, driving a damping executing mechanism to restrain the instability trend, feeding back the optimization model and the control parameters in real time, transmitting data to a remote platform, and executing shutdown and pushing early warning by a linkage braking system in emergency. The self-adaptive damping control realizes active prevention and control, closed loop optimization and control precision improvement, remote monitoring and emergency linkage safety guarantee, and the self-adaptive damping control device is adaptive to multi-scene hoisting equipment, so that the risk of instability accidents is greatly reduced.

Inventors

  • HAN JIAYIN
  • YI WEILIANG
  • LIU YONG
  • ZHANG YIFEI
  • YUAN ZE
  • ZHANG KAIGUI
  • HAN DONGYU

Assignees

  • 四川公路桥梁建设集团有限公司

Dates

Publication Date
20260505
Application Date
20260409

Claims (13)

  1. 1. The transient instability identification and self-adaptive damping control method for the hoisting equipment is characterized by comprising the following steps of: The method comprises the steps of multi-dimensional transient data acquisition, deployment of inclination angle, vibration, wind speed, load and displacement sensors, acquisition of lifting equipment landing leg inclination angle, main beam vibration amplitude, operation wind speed, lifting load weight and structural part displacement data, filtering and denoising, and transmission to a processing unit; Extracting and preprocessing instability characteristics, performing time domain and frequency domain analysis on multi-dimensional data, extracting inclination angle change rate and vibration peak characteristic parameters, and removing redundant data through maximum and minimum normalization and pearson correlation analysis; Constructing and training a transient instability identification model, constructing a long-term memory neural network, inputting a core characteristic parameter time sequence into the model, constructing a training data set by combining historical instability, normal operation and simulation instability data, and training the model by a cross verification and self-adaptive moment estimation optimization algorithm to enable the model to output a transient instability risk probability value in a 0-1 interval; judging the instability risk level, presetting a multi-level risk threshold, dynamically adjusting the threshold by combining the change trend of the core characteristic parameters, adjusting the threshold down when the characteristic parameters are rapidly increased, adjusting up when the characteristic parameters are attenuated, and triggering corresponding response when the risk is upgraded; calculating self-adaptive damping control parameters, calculating the optimal damping force according to the instability risk level, the core characteristic parameters and the equipment operation condition, and calculating the optimal adjustment rate and the action range by combining the risk level gain and the physical limit limiting constraint of the actuating mechanism; The damping executing mechanism is driven and controlled, control parameters are converted into standardized instructions, the standardized instructions are transmitted to the hydraulic or electromagnetic damper through the double-bus redundancy CAN bus, and the inclination, vibration and displacement abrupt change of equipment are restrained through the targeted structural design of the damper; the control effect is fed back and optimized in real time, the data after control is collected, the single index improvement effect is quantitatively analyzed, the comprehensive evaluation index is constructed, and a gradient descent algorithm iteration optimization model and control parameters are adopted to form closed loop control; And the remote monitoring and emergency linkage is carried out, the data such as the running state of the equipment are transmitted to a remote platform in real time, the platform supports multi-equipment management and data tracing, and the linkage braking system is in emergency stop and multi-channel early warning within 200ms when in emergency instability.
  2. 2. The method for identifying transient instability and controlling adaptive damping of hoisting equipment according to claim 1, further comprising a transient instability trend prediction step, wherein the instability development rate is calculated by a formula, and the specific formula is as follows: , Wherein, the In order to be able to develop a rate of destabilization, As the variation of the probability of instability risk per unit time, In order to provide for the time interval of time, The comprehensive variation of kernel characteristic parameters in unit time, Is the displacement variation of the device in unit time, As a weight of the probability of risk, As the weight of the characteristic parameter, Is a displacement variation weight, and 。
  3. 3. The method for identifying transient instability and controlling self-adaptive damping of lifting equipment according to claim 1, further comprising the step of compensating environmental disturbance, wherein an environmental sensor collects wind speed, temperature, humidity and ground vibration data in real time, a multivariable linear regression equation is constructed by taking environmental factors as independent variables and core data disturbance deviation as dependent variables, a coefficient is optimized and solved through a least square method, after the fitting goodness R2 is more than or equal to 0.9, a compensation coefficient is generated, the disturbance deviation calculated by a model is subtracted from an original value of the core data to complete correction, and the compensation processing delay is not more than 5ms.
  4. 4. The transient instability identification and self-adaptive damping control method for hoisting equipment according to claim 1 is characterized in that in the multi-dimensional transient data acquisition step, an inclination angle sensor is used for measuring a range of-30 degrees to 30 degrees, the precision is +/-0.05 degrees, a vibration sensor is used for measuring a range of +/-10 g, the resolution is 0.001g, a wind speed sensor is used for measuring a range of 0-60m/s, the precision is +/-0.1 m/s, a load sensor is used for measuring a range of 0-500t, the precision is +/-0.5% FS, a displacement sensor is used for measuring a range of 0-500mm, and the precision is +/-0.01 mm.
  5. 5. The transient instability identification and self-adaptive damping control method for hoisting equipment according to claim 1 is characterized in that in the instability characteristic extraction and preprocessing step, a sliding window method of 50 sampling points is adopted in time domain analysis, frequency domain analysis is used for extracting characteristic frequency of a 10Hz-100Hz frequency band through fast Fourier transformation, data are mapped to a 0-1 interval through normalization, characteristic parameters with absolute values of correlation coefficients lower than 0.3 are removed through correlation analysis, and the reserved core characteristics comprise inclination angle change rate, vibration peak value, wind speed pulsation coefficient, load fluctuation amplitude and displacement mutation characteristic values.
  6. 6. The method for identifying transient instability and self-adaptive damping control of lifting equipment according to claim 1, wherein in the step of calculating self-adaptive damping control parameters, damping force adjustment accuracy is optimized by a formula, and the specific formula is as follows: , Wherein, the For the purpose of the damping force of the object, In order to be a damping coefficient, For the destabilizing risk probability value, For differences in which the current core characteristic parameter deviates from the normal range, Is the maximum allowable deviation value of the characteristic parameter, And the value of the working condition correction coefficient is 0.8 for the no-load working condition and 1.2 for the full-load working condition.
  7. 7. The method for identifying transient instability and self-adaptive damping of lifting equipment according to claim 1, wherein in the step of driving and controlling the damping executing mechanism, the damping force adjusting range of the hydraulic damper is 0-5000N, the adjusting speed is 100N/ms, the damping force adjusting range of the electromagnetic damper is 0-3000N, the adjusting speed is 150N/ms, the command transmission delay is controlled to be not more than 20ms, and the response delay of the damping executing mechanism is controlled to be not more than 50ms.
  8. 8. The hoisting equipment transient instability identification and self-adaptive damping control method according to claim 1 is characterized in that a remote monitoring platform supports multi-equipment centralized management, the data storage time of the platform is not less than 1 year, historical data query is supported, an emergency alarm mode comprises audible and visual alarm, short message notification and APP pushing, and the alarm response time is not more than 10s.
  9. 9. A lifting device transient instability identification and adaptive damping control system for implementing a lifting device transient instability identification and adaptive damping control method according to any one of claims 1-8, characterized by comprising the following modules: The data acquisition module consists of an inclination angle, vibration, wind speed, load, displacement sensors and a data transmission unit, wherein the sensors are deployed at key parts of the equipment, and acquire multidimensional operation data in real time, and the data transmission unit adopts a 5G+ edge calculation technology; The feature processing module is used for receiving the data transmitted by the data acquisition module, executing feature extraction, normalization processing, correlation analysis and redundant data rejection operation, outputting a core feature parameter sequence, and arranging a data processing algorithm library in the module to support dynamic updating and optimization of the algorithm; The destabilization recognition module is constructed based on a long-term and short-term memory neural network and comprises a model training unit and a recognition reasoning unit, wherein the model training unit trains and optimizes model parameters through historical data and simulation data, and the recognition reasoning unit inputs a core characteristic parameter sequence and outputs a transient destabilization risk probability value; The risk judging module is used for presetting a three-level instability risk threshold value, receiving the risk probability value output by the instability identifying module, dynamically adjusting the threshold value by combining with the characteristic parameter variation trend, judging the instability risk level, triggering a corresponding response signal and supporting the manual adjustment and automatic optimization of the threshold value; The parameter calculation module is used for calculating optimal damping control parameters according to the risk level output by the risk judgment module, the core characteristic parameters output by the characteristic processing module and the equipment operation condition data, wherein the optimal damping control parameters comprise optimal damping force, optimal adjustment rate and action range calculated by combining the risk level gain and the physical limit limiting constraint of the executing mechanism, and a parameter calculation algorithm and a condition adaptation rule base are built in; the driving control module consists of a control instruction conversion unit and a CAN bus communication unit, converts the control parameters output by the parameter calculation module into standardized control instructions, transmits the standardized control instructions to the damping execution mechanism through a CAN bus, drives the damper to adjust the damping state in real time, and supports a control instruction checking and retransmitting mechanism; The feedback optimization module is used for acquiring the controlled equipment operation data through the data acquisition module, analyzing the control effect, adopting a gradient descent algorithm to iteratively optimize the instability identification model parameter and the damping control parameter, generating an optimization report and transmitting the optimization report to the related module; The remote monitoring module comprises a data storage unit, a visual display unit, an alarm unit and an emergency linkage unit, wherein the data storage unit stores running data, control instructions and optimized records of equipment, the visual display unit presents the data in a chart form, the alarm unit sends an alarm signal when the risk level is upgraded, and the emergency linkage unit is used for linking the equipment braking system under an emergency condition.
  10. 10. The transient instability identification and self-adaptive damping control system of hoisting equipment according to claim 9, wherein the sensors of the data acquisition module are in a redundant design, two sets of sensors of the same type are installed in parallel at key positions, the validity of data is verified by comparison of a data fusion algorithm, and when the data deviation of the two sets of sensors exceeds 5%, the two sets of sensors are automatically switched to the standby sensors and a fault alarm is sent out.
  11. 11. The transient instability identification and self-adaptive damping control system of hoisting equipment according to claim 9, wherein the long-term memory neural network of the instability identification module comprises 3 hidden layers, the number of hidden units in each layer is 128, the initial value of learning rate is set to be 0.001, the learning rate is adjusted by adopting a self-adaptive moment estimation optimization algorithm, the identification accuracy is not lower than 95% after model training is completed, and the AUC value on a test set is not lower than 0.98.
  12. 12. The hoisting equipment transient instability identification and adaptive damping control system according to claim 9, wherein the control command conversion unit of the drive control module supports multiple damper protocol adaptations, is compatible with different types of execution mechanisms, and the CAN bus communication unit adopts a double bus redundancy design.
  13. 13. The hoisting equipment transient instability identification and self-adaptive damping control system according to claim 9, wherein the emergency linkage unit of the remote monitoring module and the equipment braking system adopt a hard wire connection and wireless communication dual linkage mode, the hard wire connection ensures the rapid transmission of control instructions in emergency, the wireless communication is used as a backup, when the risk of emergency instability occurs, the braking system receives the instructions, then executes emergency shutdown operation within 200ms, and cuts off power output of the equipment.

Description

Transient instability identification and self-adaptive damping control method and system for hoisting equipment Technical Field The invention relates to the technical field of intelligent control of lifting equipment, in particular to a method and a system for transient instability identification and self-adaptive damping control of lifting equipment. Background The hoisting machinery is used as core equipment in the field of engineering construction, is widely applied to scenes such as buildings, bridges, ports and the like, and the stability of a steel structure directly determines construction safety and engineering progress. In the operation process of the hoisting machine, the hoisting machine is influenced by multiple factors such as hoisting load fluctuation, environmental wind interference, track flatness difference, equipment aging and abrasion and the like, transient instability symptoms such as inclination, vibration, displacement mutation and the like are very easy to appear, and if the hoisting machine is not timely identified and controlled, the hoisting machine is rapidly evolved into heavy safety accidents such as overturning, arm breakage and the like, so that serious casualties and economic losses are caused. Therefore, the precise identification and the rapid control of the transient instability of the hoisting machinery are realized, and the method becomes a key technical requirement for guaranteeing the construction safety. In the prior art, related monitoring and control schemes have advanced, but a plurality of technical bottlenecks still exist. In patent application documents with the patent publication number of CN120630821A and the patent name of a remote monitoring system for the instability of a hoisting machinery steel structure, the acquisition of inclination angle data through an inclination monitoring module is mentioned, multistage alarm and instability prediction are realized by combining an environment compensation module and a control module, monitoring precision is improved by adopting a double-shaft/three-shaft inclination angle sensor and Kalman filtering, and 5G+VR remote monitoring is supported. However, the technology focuses on instability monitoring and early warning, lacks an adaptive damping control mechanism aiming at transient instability, is difficult to restrain the instability trend through damping adjustment in the initial stage of instability only through action limitation and emergency braking to cope with risks, and has a control strategy lacking dynamic adaptation with multidimensional characteristic parameters, so that the flexibility of dealing with complex transient instability is insufficient. In the patent application document of patent publication number CN101537981B and patent name of "ultrasonic-sensor-network-based tower crane instability on-line monitoring and early warning system and method", the method has the characteristics of strong anti-interference capability and good real-time performance by adopting an ultrasonic-sensor network to monitor swing and torsion of an upper structure of a tower crane, evaluating instability through a main controller module and notifying an operator. However, the technology relies on ultrasonic ranging to realize displacement monitoring, has single monitoring dimension, does not integrate key parameters such as load, vibration and the like, can only realize passive early warning, lacks an active control executing mechanism, cannot automatically complete instability suppression, still relies on manual handling of operators, has low response speed, and is difficult to cope with millisecond-level transient instability risks. In summary, the prior art has three core limitations that firstly, the monitoring dimension is one-sided, multi-focus single physical quantity monitoring is not realized, the deep fusion of multi-dimensional data such as inclination, vibration, load, displacement and the like is not realized, the transient instability identification accuracy is insufficient, secondly, the control mode is passive, mainly alarming and emergency braking are adopted, an active damping adjustment mechanism is lacking, effective intervention cannot be carried out in an initial instability stage, thirdly, the suitability and instantaneity are insufficient, the control parameters are fixed, the instability risk level and the working condition dynamic optimization are not combined, and the data processing and control response are delayed. These problems lead to recognition lag and control inefficiency of transient instability of hoisting machinery, are difficult to meet the safety control requirement under complex construction scene, and a technical scheme integrating multidimensional monitoring, accurate recognition and self-adaptive damping control is needed, so that the bottleneck of the prior art is broken. Disclosure of Invention The invention provides a transient instability identification and self-adaptive d