Intelligent brake control system and application thereof in hoisting mechanism

Abstract

The invention discloses an intelligent braking control system and application thereof in a hoisting mechanism, and relates to the technical field of intelligent management of cranes, the system comprises a hoisting mechanism management platform building module, an acquisition module, a risk prediction module, a braking force adjusting module, an energy recovery module and an intelligent control model module. The acquisition module monitors operation data of the crane in real time and establishes a data set. And the risk prediction module predicts potential risks according to the data set, triggers early warning and adopts braking processing. The braking force adjusting module calculates and optimizes a crane braking strategy based on the real-time data to ensure safety. The energy recovery module recovers braking energy through a reverse power generation technology, and the energy utilization rate is increased. The intelligent control model is trained and optimized through a convolutional neural network, and the braking strategy of the crane is adjusted in real time in combination with multi-dimensional data. The system effectively improves the operation efficiency, the safety and the energy utilization rate of the crane, adapts to a complex working environment and provides intelligent management and control.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent management of cranes, and specifically to an intelligent braking control system and its application in a hoisting mechanism. Background Art

[0002] Traditional crane control systems have some significant deficiencies during operation, which to a certain extent affect the operating efficiency and safety of cranes. Traditional systems usually rely on static models and preset rules, lacking the ability to respond in real time to the dynamic working environment, and failing to fully consider the comprehensive analysis of real-time data, such as wind force changes, load fluctuations, and crane speed. These factors pose potential threats to the safe operation of cranes. Due to the lack of real-time monitoring and risk assessment of multiple variables, traditional systems often can only perform simple processing based on experience, resulting in the inability to give effective early warnings and adjustments at the initial stage of risks.

[0003] In addition, the management of traditional crane control systems in terms of braking and energy recovery is relatively simple, and it is difficult to achieve dynamic adjustment based on real-time data. The setting of braking force is usually fixed, lacking the function of automatic adjustment according to specific working conditions, resulting in low braking efficiency of the crane in some complex working conditions, and even possible braking failure. In terms of energy recovery, traditional systems cannot evaluate and optimize the energy recovery effect in real time, often resulting in low recovery efficiency and wasting precious energy.

[0004] During the management and scheduling process of the entire crane system, traditional methods rely too much on manual operation or simple rule judgment, lacking intelligent support. Facing the complex and changeable working environment, the response ability of traditional systems is limited, and they cannot adapt and adjust work strategies in real time, thus affecting the overall operation efficiency and safety. Therefore, improving the intelligent level of the crane system, being able to obtain and process multi-dimensional data in real time, predict and warn of potential risks, and optimize braking and energy recovery strategies has become an important direction for current system improvement. Summary of the Invention

[0005] Aiming at the deficiencies of the prior art, the present invention provides an intelligent braking control system and its application in a hoisting mechanism to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: An intelligent braking control system and its application in a hoisting mechanism, including: Building a management platform module for the hoisting mechanism, a collection module, a risk prediction module, a braking force adjustment module, an energy recovery function module, and an intelligent control model module; Build a management platform module for lifting mechanisms, which is used to interact with different lifting mechanisms within the lifting mechanism management platform and provide a visual interface to obtain the operating status information of the lifting mechanisms in real time; A data acquisition module, which is used to monitor and record the operating data of the lifting mechanism in real time, including the total mass M of the crane, the load weight L of the crane, the moving speed V of the crane, the vibration acceleration A, the brake pressure p of the crane, the inclination angle of the crane , the height h of the crane load, the temperature of the braking equipment , the braking friction force , the braking duration t, the electric energy actually recovered by the crane and the real-time wind force value received by the crane , and establish a data set; A risk prediction module, which is used to monitor the operating status of the crane in real time based on the data set, predict the risks during the operation of the crane, trigger a warning instruction for the risk situation, and take braking measures; A braking force adjustment module, which is used to calculate and obtain the braking force F of the crane based on the data set, calculate and obtain the safety braking adjustment coefficient DTx according to the braking force F of the crane, and optimize and adjust the braking of the crane; An energy recovery function module, which is used to recover the excess kinetic energy through reverse power generation technology during the braking process, convert the energy generated during the braking process into electric energy and store it, evaluate the electric energy recovery effect through the energy recovery coefficient NLx, and ensure the energy conservation of the system; An intelligent prediction module, which is used to use a convolutional neural network to build an initial convolutional neural network model, train and test the initial convolutional neural network model with historical operating data and real-time monitoring data, and use the initial convolutional neural network model after training as an intelligent control model. At the same time, use the intermediate layer output of the braking force, safety braking adjustment coefficient and energy recovery coefficient data of the crane as feature vectors to identify feature information, and train and test the intelligent control model with the obtained feature information. Use the trained intelligent control model to safely brake the crane during operation.

[0007] Preferably, the data acquisition module is used to install sensors on the lifting mechanism to monitor and record the operating data of the lifting mechanism in real time, including the total mass M of the crane, the load weight L of the crane, the moving speed V of the crane, the vibration acceleration A, the brake pressure p of the crane, the inclination angle of the crane , the height h of the crane load, the braking duration t, the braking friction force ; collect the temperature of the braking equipment by installing a temperature sensor ; collect the electric energy actually recovered by the crane by installing a voltage sensor ; collect the real-time wind force value received by the crane by installing a wind sensor and establish a data set.

[0008] Preferably, the risk prediction module includes: a first calculation unit and a first evaluation unit; The first calculation unit is used to extract the data set, monitor the running state of the crane in real time, and after dimensionless processing, calculate and obtain the predicted risk coefficient YCx. The formula is as follows: ; In the formula, L represents the load weight of the crane, represents the maximum load weight of the crane, represents the real-time wind force value received by the crane, represents the maximum wind force value that the crane can withstand, h represents the height of the crane load, represents the inclination angle of the crane, V represents the running speed of the crane, represents the maximum running speed of the crane, and a1, a2, a3, and a4 represent weight coefficients.

[0009] Preferably, the first evaluation unit is used to preset a first standard threshold K in advance, and compare and analyze the predicted risk coefficient YCx with the first standard threshold K to obtain a first evaluation result, including: When the predicted risk coefficient YCx < the first standard threshold K, it means that there is no risk during the operation of the crane, and continuous monitoring is carried out; When the predicted risk coefficient YCx ≥ the first standard threshold K, it means that there is a risk during the operation of the crane, trigger a first warning instruction, generate a first strategy, and take braking treatment on the crane.

[0010] Preferably, the braking force adjustment module includes: a second calculation unit, a third calculation unit, and a second evaluation unit; The second calculation unit is used to extract the data set data when receiving the first warning instruction, including the load weight L, braking friction and braking duration t. After dimensionless processing, calculate and obtain the braking force F of the crane. The formula is as follows: ; In the formula, represents the final speed of the crane; The third calculation unit calculates and obtains the safety braking adjustment coefficient DTx through the braking force F of the heavy machine and the data set data, including the load weight L of the crane, the moving speed V of the crane, the vibration acceleration A of the crane, the brake pressure p of the crane, the inclination angle of the crane , braking equipment temperature , the friction force generated by braking and braking duration t. After dimensionless processing, the formula is as follows: ; In the formula, represents the maximum temperature value borne by the braking device, and w1, w2, w3, w4, and w5 represent weight coefficients.

[0011] Preferably, the second evaluation unit is used to preset a second standard threshold Q in advance, and compare and analyze the safety braking adjustment coefficient DTx with the second standard threshold Q to obtain the second evaluation result, including: When the safety braking adjustment coefficient DTx ≥ the second standard threshold Q, it means that the crane braking has no risk of braking failure, no adjustment is made, and continuous monitoring is carried out; When the safety braking adjustment coefficient DTx < the second standard threshold Q, it means that the crane braking has a risk of braking failure, trigger the second warning instruction, and generate the second strategy, including: reducing the load weight by 10%, reducing the moving speed by 8%, and reducing the vibration acceleration by 5%. After adjustment, recalculate until the safety braking adjustment coefficient DTx ≥ the second standard threshold Q.

[0012] Preferably, the energy recovery function module includes: a fourth calculation unit and a third evaluation unit; The fourth calculation unit is used to recover the excess kinetic energy through reverse power generation technology during the braking process of the crane, convert the energy generated during the braking process into electric energy and store it. After dimensionless processing, calculate and obtain the energy recovery coefficient NLx. The formula is as follows: ; In the formula, represents the electric energy actually recovered by the crane, M represents the total mass of the crane, V represents the speed of the crane, represents the final speed of the crane, t represents the braking duration of the crane, represents the friction force generated by the crane braking, represents the friction energy conversion coefficient, which is obtained through test data, .

[0013] Preferably, the third evaluation unit is used to preset a third standard threshold X in advance, and compare and analyze the energy recovery coefficient NLx with the third standard threshold X to obtain the third evaluation result, including: When the energy recovery coefficient NLx ≥ the third standard threshold X, it means that during the braking process of the crane, the energy that has been consumed is converted into electric energy for energy-saving effect, no adjustment is made, and continuous monitoring is carried out; When the energy recovery coefficient NLx < the third standard threshold X, it indicates that during the braking process of the crane, the energy that has been consumed is converted into electrical energy for the energy consumption effect, triggering the third warning instruction. The third strategy generated includes: using a cooling system to cool the braking equipment to increase the friction force by 10%, reduce the braking duration by 8% - 10%, and recalculate until the energy recovery coefficient NLx ≥ the third standard threshold X.

[0014] Preferably, the intelligent control model module is used to construct an initial convolutional neural network model using a convolutional neural network, and train and test the initial convolutional neural network model with historical operation data and real-time monitoring data. The trained initial convolutional neural network model is used as the intelligent control model. At the same time, the intermediate layer output of the braking force, safety braking adjustment coefficient, and energy recovery coefficient data of the crane is used as the feature vector to identify the feature information, and the intelligent control model is trained and tested with the obtained feature information. The trained intelligent control model is used for the safety braking of the crane during intelligent control operation.

[0015] Preferably, the application of intelligent braking control in the lifting mechanism includes the intelligent braking control system described in any one of claims 1 - 9, and includes the following steps: S1. Build a lifting mechanism management platform, interact with different lifting mechanisms within the lifting mechanism management platform, and provide a visual interface to obtain the operation status information of the lifting mechanism in real time; S2. Real-time monitor and record the operation data of the lifting mechanism, including the total mass M of the crane, the load weight L of the crane, the moving speed V of the crane, the vibration acceleration A, the brake pressure p of the crane, the inclination angle of the crane, the height h of the crane load, the temperature of the braking equipment the braking friction force the braking duration t, the electrical energy actually recovered by the crane and the real-time wind force value received by the crane , and establish a data set; S3. Real-time monitor the operation status of the crane, calculate and obtain the predicted risk coefficient YCx, and conduct an evaluation to predict the risk during the operation of the crane, trigger the first warning instruction, and take braking measures; S4. When receiving the first warning instruction, combine the data set, calculate and obtain the braking force F of the crane, calculate and obtain the safety braking adjustment coefficient DTx based on the braking force F of the crane, and conduct an analysis and evaluation to optimize and adjust the braking of the crane; S5. During the braking process, recover the excess kinetic energy through regenerative power generation technology, convert the energy generated during the braking process into electrical energy and store it, and evaluate the electrical energy recovery effect through the energy recovery coefficient NLx to ensure the energy conservation of the system; S6. Using a convolutional neural network, construct an initial convolutional neural network model, and train and test the initial convolutional neural network model with historical operation data and real-time monitoring data. Then, use the trained initial convolutional neural network model as the intelligent control model. At the same time, use the intermediate layer output of the braking force, safety braking adjustment coefficient, and energy recovery coefficient data of the crane as the feature vector to identify the feature information, and train and test the intelligent control model with the obtained feature information. Use the trained intelligent control model for the safety braking of the crane during intelligent control operation.

[0016] The present invention provides an intelligent braking control system and its application in a hoisting mechanism, having the following beneficial effects: (1) For the intelligent braking control system and its application in a hoisting mechanism, the prediction risk coefficient YCx is calculated and obtained by the risk prediction module based on the dataset data. The system can monitor the running state of the crane in real time, predict potential risks, and trigger warning instructions. Compared with traditional systems, intelligent control can take corresponding countermeasures before danger occurs, effectively reducing the probability of accidents and ensuring the safety of equipment and personnel.

[0017] (2) For the intelligent braking control system and its application in a hoisting mechanism, the safety braking adjustment coefficient DTx is calculated and adjusted in real time by the braking force adjustment module, and the braking strategy can be automatically optimized according to different working conditions, including load, speed, and vibration acceleration. Compared with traditional static braking control, the system can improve the braking efficiency under complex working conditions, avoid braking failure or uneven braking phenomena, thereby improving operation safety and work efficiency.

[0018] (3) For the intelligent braking control system and its application in a hoisting mechanism, the redundant kinetic energy of the crane during braking is recovered through the reverse power generation technology of the energy recovery function module, converted into electric energy and stored. This function achieves the best recovery effect under dynamic regulation, greatly improving the energy utilization rate, saving energy and reducing operating costs compared with traditional systems.

[0019] (4) For the intelligent braking control system and its application in a hoisting mechanism, an intelligent control model is constructed by the intelligent prediction module, and intelligent prediction, braking force adjustment, and energy recovery functions are introduced. The system can comprehensively evaluate various indicators, such as safety, efficiency, and energy conservation, and optimize the system performance as a whole. This multi-dimensional intelligent optimization not only improves the working efficiency of the crane but also ensures the sustainable operation of the equipment and reduces the long-term operating costs of the system. Description of the Drawings

[0020] Figure 1 It is a schematic diagram of the block diagram process of the intelligent braking control system of the present invention; Figure 2Schematic diagram of the intelligent braking control system of the present invention and its application steps in a hoisting mechanism. Specific implementation manners

[0021] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0022] Embodiment 1 Please refer to Figure 1 , the present invention provides an intelligent braking control system, including: a hoisting mechanism management platform module, a collection module, a risk prediction module, a braking force adjustment module, an energy recovery function module, and an intelligent control model module; The hoisting mechanism management platform module is used to interact with different hoisting mechanisms within the hoisting mechanism management platform, provide a visual interface, and obtain the operation status information of the hoisting mechanism in real time; The collection module is used to monitor and record the operation data of the hoisting mechanism in real time, including the total mass M of the crane, the load weight L of the crane, the moving speed V of the crane, the vibration acceleration A, the brake pressure p of the crane, the inclination angle of the crane , the height h of the crane load, the temperature of the braking equipment , the braking friction , the braking duration t, the electric energy actually recovered by the crane and the real-time wind force value received by the crane , and establish a data set; The risk prediction module is used to monitor the operation status of the crane in real time based on the data set, predict the risks during the operation of the crane, and trigger a warning instruction for the risk situation and take braking treatment; The braking force adjustment module is used to calculate and obtain the braking force F of the crane based on the data set, calculate and obtain the safety braking adjustment coefficient DTx according to the braking force F of the crane, and optimize and adjust the braking of the crane; The energy recovery function module is used to recover the excess kinetic energy through reverse power generation technology during the braking process, convert the energy generated during the braking process into electric energy and store it, evaluate the electric energy recovery effect through the energy recovery coefficient NLx, and ensure the energy conservation of the system; An intelligent prediction module is used to construct an initial convolutional neural network model using a convolutional neural network, and train and test the initial convolutional neural network model with historical operation data and real-time monitoring data, and use the trained initial convolutional neural network model as an intelligent control model. At the same time, the intermediate layer output of the braking force, safety braking adjustment coefficient, and energy recovery coefficient data of the crane is used as a feature vector to identify feature information, and the intelligent control model is trained and tested through the obtained feature information. The trained intelligent control model is used for the safety braking of the crane during intelligent control operation.

[0023] In this embodiment, the prediction risk coefficient YCx is calculated and obtained by the risk prediction module based on the dataset data. The system can monitor the operating state of the crane in real time, predict potential risks, and trigger warning instructions. The safety braking adjustment coefficient DTx is calculated and adjusted in real time by the braking force adjustment module, which can automatically optimize the braking strategy according to different working conditions, including load, speed, and vibration acceleration. Compared with traditional static braking control, the system can improve the braking efficiency under complex working conditions, avoid braking failure or uneven braking phenomena, thereby improving operation safety and work efficiency. The redundant kinetic energy of the crane during braking is recovered through the reverse power generation technology of the energy recovery function module, converted into electrical energy and stored. This function achieves the best recovery effect under the dynamic adjustment of the energy recovery coefficient NLx, greatly improving the energy utilization rate. By constructing an intelligent control model through the intelligent prediction module, various indicators such as safety, efficiency, and energy conservation can be comprehensively evaluated, and the system performance can be optimized as a whole.

[0024] Embodiment 2 This embodiment is an explanatory description based on Embodiment 1. Specifically, the acquisition module is used to install sensors on the hoisting mechanism to monitor and record various operating data of the hoisting mechanism in real time, including the total mass M of the crane, the load weight L of the crane, the moving speed V of the crane, the vibration acceleration A, the brake pressure p of the crane, the inclination angle of the crane , the height h of the crane load, the braking duration t, the braking friction ; the temperature of the braking equipment is collected by installing a temperature sensor ; the actual electrical energy recovered by the crane is collected by installing a voltage sensor ; the real-time wind force value received by the crane is collected by installing a wind sensor , and a dataset is established.

[0025] In this embodiment, by installing a variety of sensors on the hoisting mechanism to collect a number of key data including the total mass of the crane, load weight, moving speed, vibration acceleration, etc., the system can monitor the operating state of the equipment in real time. This real-time data acquisition ability can provide more comprehensive and accurate information support for intelligent decision-making and provide a scientific basis for subsequent calculations.

[0026] Example 3 This example is an explanatory note based on Example 2. Specifically, the risk prediction module includes: a first calculation unit and a first evaluation unit; The first calculation unit is used to extract the data set, monitor the operating state of the crane in real time, and after dimensionless processing, calculate and obtain the predicted risk coefficient YCx. The formula is as follows: ; In the formula, L represents the load weight of the crane, represents the maximum load weight of the crane, represents the real-time wind force value received by the crane, represents the maximum wind force value that the crane can withstand, h represents the height of the crane load, represents the inclination angle of the crane, V represents the operating speed of the crane, represents the maximum operating speed of the crane, a1, a2, a3, and a4 represent weight coefficients, , , and , and .

[0027] In this example, based on real-time data, the system can monitor the operating state of the crane in real time and calculate the predicted risk coefficient using the dimensionless processed data. This method can comprehensively consider various influencing factors including load weight, wind force, inclination angle, and operating speed, identify potential risks in advance and trigger warnings, thus significantly improving the accuracy and objectivity of the calculation.

[0028] Example 4 This example is an explanatory note based on Example 3. Please refer to Figure 1 , specifically, the first evaluation unit is used to preset the first standard threshold K in advance, and compare and analyze the predicted risk coefficient YCx with the first standard threshold K to obtain the first evaluation result, including: when the predicted risk coefficient YCx < the first standard threshold K, it means that there is no risk during the operation of the crane, and continuous monitoring is carried out; When the predicted risk coefficient YCx ≥ the first standard threshold K, it means that there is a risk during the operation of the crane, trigger the first warning instruction, generate the first strategy, and take braking treatment on the crane.

[0029] In this embodiment, by introducing the first evaluation unit, the system can evaluate the predicted risk coefficient in real time and conduct a comparative analysis with a preset standard threshold. When the risk coefficient reaches or exceeds the set threshold, the system can automatically trigger a warning instruction and generate corresponding countermeasures, and initiate the braking process in a timely manner. This intelligent evaluation and response mechanism can make timely adjustments before the risk occurs, effectively avoiding the possible slow reaction and mistakes in the traditional control system, and significantly improving the safety and stability of the crane operation.

[0030] Embodiment 5 This embodiment is an explanatory description based on Embodiment 4. Please refer to Figure 1 , specifically, the braking force adjustment module includes: a second calculation unit, a third calculation unit, and a second evaluation unit; The second calculation unit is used to extract the data set data when receiving the first warning instruction, including the load weight L, braking friction and braking duration t. After dimensionless processing, the braking force F of the crane is calculated as follows: ; In the formula, represents the final speed of the crane; The third calculation unit calculates and obtains the safety braking adjustment coefficient DTx according to the braking force F of the heavy machine and the data set data, including the load weight L of the crane, the moving speed V of the crane, the vibration acceleration A of the crane, the brake pressure p of the crane, the inclination angle of the crane , the temperature of the braking equipment , the friction force generated by braking and braking duration t. After dimensionless processing, the formula is as follows: ; In the formula, represents the maximum temperature value that the braking equipment can withstand, w1, w2, w3, w4, and w5 represent weight coefficients, , , , and , and .

[0031] In this embodiment, after receiving the first warning instruction, the braking force of the crane is dynamically calculated and optimized according to the real-time data including the load weight, braking friction, and braking duration. This real-time adjustment mechanism ensures the braking efficiency in a complex working environment, effectively preventing the occurrence of braking failure or uneven braking, thereby improving the safety and stability of the crane operation.

[0032] Embodiment 6 This embodiment is an explanatory description carried out in Embodiment 5. Please refer to Figure 1 , specifically, the second evaluation unit is used to obtain the second evaluation result by presetting a second standard threshold Q in advance and comparing and analyzing the safety braking adjustment coefficient DTx with the second standard threshold Q, including: When the safety braking adjustment coefficient DTx ≥ the second standard threshold Q, it indicates that the crane braking has no risk of braking failure, no adjustment is made, and continuous monitoring is carried out; When the safety braking adjustment coefficient DTx < the second standard threshold Q, it indicates that the crane braking has a risk of braking failure, triggering a second warning instruction and generating a second strategy, including: reducing the load weight by 10%, reducing the moving speed by 8%, and reducing the vibration acceleration by 5%. After adjustment, recalculate until the safety braking adjustment coefficient DTx ≥ the second standard threshold Q.

[0033] In this embodiment, by introducing the second evaluation unit, the system can evaluate the safety braking adjustment coefficient in real time and compare it with the preset standard threshold. When the system detects a risk of braking failure, it will automatically trigger a warning and take a series of adjustment measures, such as reducing the load, reducing the moving speed, and vibration acceleration. This adaptive adjustment mechanism can ensure the safe operation of the crane under high-risk working conditions, avoid operation errors that may occur due to ignoring risks in the traditional system, and improve the safety and reliability of crane operation.

[0034] Embodiment 7 This embodiment is an explanatory description carried out in Embodiment 6. Please refer to Figure 1 , specifically, the energy recovery function module includes: a fourth calculation unit and a third evaluation unit; The fourth calculation unit is used to recover the excess kinetic energy through reverse power generation technology during the braking process of the crane, convert the energy generated during braking into electrical energy and store it. After dimensionless processing, calculate and obtain the energy recovery coefficient NLx, and the formula is as follows: ; In the formula, represents the actual electrical energy recovered by the crane, M represents the total mass of the crane, V represents the speed of the crane, represents the final speed of the crane, t represents the braking duration of the crane, represents the friction force generated by the crane braking, represents the friction energy conversion coefficient, which is obtained through test data, .

[0035] In this embodiment, by introducing an energy recovery function module, the system can utilize reverse power generation technology to recover excess kinetic energy during the braking process of the crane and convert it into electrical energy for storage. The fourth calculation unit calculates the energy recovery coefficient NLx in real time to optimize the energy recovery process, thereby significantly improving the recovery efficiency. Compared with traditional crane systems, the intelligent energy recovery mechanism can minimize energy waste, reduce energy consumption, lower operating costs, improve the overall energy utilization efficiency of the system, and thus achieve energy conservation and environmental protection goals.

[0036] Embodiment 8 This embodiment is an explanatory description based on Embodiment 7. Please refer to Figure 1 , specifically, the third evaluation unit is used to preset a third standard threshold X in advance and compare and analyze the energy recovery coefficient NLx with the third standard threshold X to obtain a third evaluation result, including: When the energy recovery coefficient NLx ≥ the third standard threshold X, it indicates that during the braking process of the crane, the energy that has been consumed is converted into electrical energy for energy-saving effect, without adjustment, and continuous monitoring is carried out; When the energy recovery coefficient NLx < the third standard threshold X, it indicates that during the braking process of the crane, the energy that has been consumed is converted into electrical energy for energy-consuming effect, triggering a third warning instruction, and generating a third strategy including: using a cooling system to cool the braking equipment to increase the friction force by 10%, reduce the braking duration by 8% - 10%, recalculate until the energy recovery coefficient NLx ≥ the third standard threshold X.

[0037] In this embodiment, by introducing the third evaluation unit and setting the standard threshold of the energy recovery coefficient NLx, the system can monitor the energy recovery effect of the crane in real time and make dynamic adjustments according to the actual recovery situation. When the recovery efficiency does not meet the expectation, the system will automatically trigger a warning and take corresponding measures, such as adjusting the friction force through a cooling system, shortening the braking duration, etc., to optimize the braking process. This intelligent adjustment significantly improves the energy recovery efficiency and ensures that during the braking process of the crane, energy waste can be minimized to achieve energy-saving effects.

[0038] Embodiment 9 This embodiment is an explanatory description based on Embodiment 8. Please refer to Figure 1, specifically, the intelligent control model module is used to build an initial convolutional neural network model using a convolutional neural network, and train and test the initial convolutional neural network model with historical operation data and real-time monitoring data, and use the trained initial convolutional neural network model as the intelligent control model. At the same time, the intermediate layer output of the braking force, safety braking adjustment coefficient, and energy recovery coefficient data of the crane is used as a feature vector to identify feature information, and the intelligent control model is trained and tested with the obtained feature information, and the trained intelligent control model is used as the safety braking for the crane operating intelligently.

[0039] In this embodiment, by using a convolutional neural network (CNN) to build an intelligent control model and combining historical operation data and real-time monitoring data for training and testing, the system can accurately identify the safety and performance characteristics of the crane under different working conditions. The intelligent control model can adjust the control strategy in real time according to the real-time monitored braking force, safety braking adjustment coefficient, and energy recovery coefficient data, optimize the braking process, and improve the energy recovery efficiency. Compared with traditional control methods, this intelligent control model has stronger adaptability and accuracy, can effectively reduce the dependence on human intervention, give early warnings of potential safety risks in real time, optimize the operation process, and improve the overall operation safety and work efficiency.

[0040] Embodiment 10 For the application of intelligent braking control in a hoisting mechanism, please refer to Figure 2 , including the following steps: S1. Build a hoisting mechanism management platform, interact with different hoisting mechanisms within the hoisting mechanism management platform, and provide a visual interface to obtain the operation status information of the hoisting mechanism in real time; S2. Monitor and record the operation data of the hoisting mechanism in real time, including the total mass M of the crane, the load weight L of the crane, the moving speed V of the crane, the vibration acceleration A, the brake pressure p of the crane, the inclination angle of the crane , the height h of the crane load, the temperature of the braking equipment , the braking friction , the braking duration t, the electric energy actually recovered by the crane and the real-time wind force value received by the crane , and establish a data set; S3. Monitor the operation status of the crane in real time, calculate and obtain the predicted risk coefficient YCx, and evaluate it to predict the risk during the operation of the crane, trigger the first warning instruction, and take braking measures; S4. When receiving the first warning instruction, combine the data set, calculate and obtain the braking force F of the crane, and calculate and obtain the safety braking adjustment coefficient DTx based on the braking force F of the crane, and conduct analysis and evaluation to optimize and adjust the braking of the crane; S5. During the braking process, redundant kinetic energy is recovered through reverse power generation technology, and the energy generated during braking is converted into electrical energy and stored. The power recovery effect is evaluated through the energy recovery coefficient NLx to ensure energy conservation of the system. S6. Using a convolutional neural network, an initial convolutional neural network model is constructed, and the initial convolutional neural network model is trained and tested with historical operation data and real-time monitoring data. The trained initial convolutional neural network model is used as an intelligent control model. At the same time, the intermediate layer output of the braking force, safety braking adjustment coefficient, and energy recovery coefficient data of the crane is used as a feature vector to identify feature information, and the intelligent control model is trained and tested with the obtained feature information. The trained intelligent control model is used for the safe braking of the crane during intelligent control operation.

[0041] In this embodiment, the application of intelligent braking control in the hoisting mechanism is achieved by building a hoisting mechanism management platform, collecting dataset data, calculating and obtaining the predicted risk coefficient YCx. The system can monitor the operating state of the crane in real time, predict potential risks and trigger warning instructions, and calculate and adjust the safety braking adjustment coefficient DTx in real time. It can automatically optimize the braking strategy according to different working conditions, including load, speed, and vibration acceleration. Compared with traditional static braking control, the system can improve braking efficiency under complex working conditions, avoid braking failure or uneven braking phenomena, thereby improving operation safety and work efficiency; redundant kinetic energy during the braking process of the crane is recovered through reverse power generation technology and converted into electrical energy and stored. This function achieves the best recovery effect under dynamic adjustment of the energy recovery coefficient NLx, greatly improving energy utilization efficiency; an intelligent control model is constructed through an intelligent prediction module, which can comprehensively evaluate various indicators, such as safety, efficiency, energy conservation, etc., and optimize the system performance as a whole.

[0042] The setting of the threshold value is for the convenience of comparison. Regarding the size of the threshold value, it depends on the amount of sample data and the base quantity set by those skilled in the art for each group of sample data; as long as the proportional relationship between the parameter and the quantized value is not affected.

[0043] The above formulas are all obtained by collecting a large amount of data for software simulation and selecting a formula close to the true value. The coefficients in the formula are set by those skilled in the art according to the actual situation. As described above, only the preferred specific embodiments of the present invention are given, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.

Claims

1. Intelligent braking control system, characterized by: It includes building a lifting mechanism management platform module, a collection module, a risk prediction module, a braking force adjustment module, an energy recovery function module and an intelligent control model module; The hoisting mechanism management platform module is used to interact with different hoisting mechanisms in the hoisting mechanism management platform and provide a visual interface to obtain the operation status information of the hoisting mechanism in real time; The acquisition module is used to monitor and record various operating data of the crane mechanism in real time, including the total mass M of the crane, the load weight L of the crane, the movement speed V of the crane, the vibration acceleration A, the brake pressure p of the crane, the tilt angle of the crane , height of crane load h, brake equipment temperature , Braking friction , braking time t, actual electrical energy recovered by the crane and the real-time wind force value of the crane , and build a data set; The risk prediction module is used to monitor the operating status of the crane in real time based on the data set, predict the risks during the operation of the crane, trigger early warning instructions for risk situations, and take braking measures; The braking force adjustment module is used to calculate and obtain the braking force F of the crane based on the data set, calculate and obtain the safety braking adjustment coefficient DTx according to the braking force F of the crane, and optimize and adjust the braking of the crane; The energy recovery function module is used to recover excess kinetic energy during braking through reverse power generation technology, convert the energy generated during braking into electrical energy and store it. The energy recovery coefficient NLx is used to evaluate the electrical energy recovery effect to ensure energy conservation of the system; The intelligent prediction module is used to use the convolutional neural network to build an initial model of the convolutional neural network, and to train and test the initial model of the convolutional neural network with historical operation data and real-time monitoring data, and to use the trained initial model of the convolutional neural network as the intelligent control model. At the same time, the intermediate layer output of the crane's braking force, safety braking adjustment coefficient and energy recovery coefficient data is used as a feature vector to identify feature information, and the intelligent control model is trained and tested through the acquired feature information, and the trained intelligent control model is used as the intelligent control to operate the crane's safety braking.

2. The intelligent braking control system according to claim 1, characterized in that: The acquisition module is used to install sensors on the lifting mechanism to monitor and record various operating data of the lifting mechanism in real time, including the total mass M of the crane, the load weight L of the crane, the movement speed V of the crane, the vibration acceleration A, the brake pressure p of the crane, and the tilt angle of the crane. , height of crane load h, braking time t, braking friction ; Collect the brake equipment temperature by installing a temperature sensor ; Collect the actual electrical energy recovered by the crane by installing voltage sensors ; By installing wind sensors, the real-time wind force values ​​of the crane can be collected. , and create a data set.

3. The intelligent braking control system according to claim 2, characterized in that: The risk prediction module includes: a first calculation unit and a first evaluation unit; The first calculation unit is used to extract the data set, monitor the operation status of the crane in real time, and calculate and obtain the predicted risk coefficient YCx after dimensionless processing. The formula is as follows: ； In the formula, L represents the load weight of the crane, Indicates the maximum load weight of the crane. Indicates the real-time wind force value of the crane. It indicates the maximum wind force that the crane can withstand, and h indicates the height of the crane load. represents the tilt angle of the crane, V represents the operating speed of the crane, It represents the maximum operating speed of the crane, and a1, a2, a3 and a4 represent weight coefficients.

4. The intelligent braking control system according to claim 3, characterized in that: The first evaluation unit is used to preset a first standard threshold K in advance, and compare and analyze the predicted risk coefficient YCx with the first standard threshold K to obtain a first evaluation result, including: When the predicted risk factor YCx is less than the first standard threshold K, it means that there is no risk in the operation of the crane and continuous monitoring is required; When the predicted risk coefficient YCx ≥ the first standard threshold K, it means that there is a risk in the operation of the crane, triggering the first warning instruction, generating the first strategy, and taking braking action on the crane.

5. The intelligent braking control system according to claim 4, characterized in that: The braking force adjustment module includes: a second calculation unit, a third calculation unit and a second evaluation unit; The second calculation unit is used to extract data from the data set when receiving the first warning instruction, including the load weight L, the braking friction and the braking time t, after dimensionless processing, the braking force F of the crane is calculated, and the formula is as follows: ； In the formula, Indicates the final speed of the crane; The third calculation unit calculates the braking force F of the crane and the data set data, including the load weight L of the crane, the movement speed V of the crane, the vibration acceleration A of the crane, the brake pressure p of the crane, and the tilt angle of the crane. , Braking equipment temperature , the friction force generated by braking And the braking time t, after dimensionless processing, calculate the safety braking adjustment coefficient DTx, the formula is as follows: ； In the formula, It represents the maximum temperature value that the braking equipment can withstand, and w1, w2, w3, w4 and w5 represent weight coefficients.

6. The intelligent braking control system according to claim 5, characterized in that: The second evaluation unit is used to preset the second standard threshold value Q in advance, and compare and analyze the safety braking adjustment coefficient DTx with the second standard threshold value Q to obtain the second evaluation result, including: When the safety brake adjustment coefficient DTx ≥ the second standard threshold Q, it means that there is no risk of brake failure in the crane brake, and no adjustment is made, and continuous monitoring is performed; When the safety braking adjustment coefficient DTx is less than the second standard threshold value Q, it indicates that there is a risk of brake failure in the crane braking, triggering the second warning instruction and generating the second strategy, including: reducing the load weight by 10%, reducing the movement speed by 8% and reducing the vibration acceleration by 5%, and recalculating after adjustment until the safety braking adjustment coefficient DTx is greater than or equal to the second standard threshold value Q.

7. The intelligent braking control system according to claim 6, characterized in that: The energy recovery functional module includes: a fourth calculation unit and a third evaluation unit; The fourth calculation unit is used to recover excess kinetic energy during the braking process of the crane through reverse power generation technology, convert the energy generated during the braking process into electrical energy and store it. After dimensionless processing, the energy recovery coefficient NLx is calculated and obtained. The formula is as follows: ； In the formula, represents the actual electrical energy recovered by the crane, M represents the total mass of the crane, V represents the speed of the crane, represents the final speed of the crane, t represents the duration of the crane braking, Indicates the friction force generated by the crane brake, Represents the friction energy conversion coefficient, obtained through test data, .

8. The intelligent braking control system according to claim 7, characterized in that: The third evaluation unit is used to preset a third standard threshold value X in advance, and compare and analyze the energy recovery coefficient NLx with the third standard threshold value X to obtain a third evaluation result, including: When the energy recovery coefficient NLx ≥ the third standard threshold value X, it means that during the braking process, the crane uses the consumed energy to convert into electrical energy for energy saving effect, and no adjustment is made, and continuous monitoring is performed; When the energy recovery coefficient NLx is less than the third standard threshold value X, it means that during the braking process, the crane uses the consumed energy to convert into electrical energy as the energy consumption effect, triggering the third early warning instruction and generating the third strategy, including: using the cooling system to cool the braking equipment to increase the friction by 10%, reducing the braking time by 8%-10%, and recalculating until the energy recovery coefficient NLx is greater than or equal to the third standard threshold value X.

9. The intelligent braking control system according to claim 8, characterized in that: The intelligent control model module is used to use a convolutional neural network to construct an initial model of the convolutional neural network, and to train and test the initial model of the convolutional neural network with historical operation data and real-time monitoring data, and to use the trained initial model of the convolutional neural network as an intelligent control model. At the same time, the intermediate layer output of the braking force, safety braking adjustment coefficient and energy recovery coefficient data of the crane is used as a feature vector to identify feature information, and the intelligent control model is trained and tested through the acquired feature information, and the trained intelligent control model is used as the intelligent control to operate the safety braking of the crane.

10. Application of intelligent braking control in a lifting mechanism, comprising the intelligent braking control system according to any one of claims 1 to 9, comprising the following steps: S1. Build a lifting mechanism management platform, interact with different lifting mechanisms in the lifting mechanism management platform, and provide a visual interface to obtain the operating status information of the lifting mechanism in real time; S2. Real-time monitoring and recording of various operating data of the lifting mechanism, including the total mass M of the crane, the load weight L of the crane, the movement speed V of the crane, the vibration acceleration A, the brake pressure p of the crane, and the tilt angle of the crane. , height of crane load h, brake equipment temperature , Braking friction , braking time t, actual electrical energy recovered by the crane and the real-time wind force value of the crane , and build a data set; S3, monitor the operation status of the crane in real time, calculate and obtain the predicted risk coefficient YCx, and evaluate it, predict the risk during the operation of the crane, trigger the first warning instruction, and take braking measures; S4. When the first warning instruction is received, the braking force F of the crane is calculated and obtained in combination with the data set. According to the braking force F of the crane, the safety braking adjustment coefficient DTx is calculated and obtained, and analysis and evaluation are performed to optimize the braking of the crane. S5. During braking, excess kinetic energy is recovered through reverse power generation technology. The energy generated during braking is converted into electrical energy and stored. The energy recovery coefficient NLx is used to evaluate the effect of electrical energy recovery to ensure energy conservation of the system. S6. Use convolutional neural networks to construct an initial model of the convolutional neural network, and use historical operation data and real-time monitoring data to train and test the initial model of the convolutional neural network. The trained initial model of the convolutional neural network is used as an intelligent control model. At the same time, the intermediate layer output of the crane's braking force, safety braking adjustment coefficient and energy recovery coefficient data is used as a feature vector to identify feature information. The intelligent control model is trained and tested through the acquired feature information, and the trained intelligent control model is used as the intelligent control to operate the crane's safety braking.

Images