A method and system for automatic jacking

Abstract

The application provides an automatic turning method and system, and relates to the technical field of power station maintenance, comprising: obtaining first information and second information, the first information is a sensor deployment scheme, sensor data and corresponding turning effect evaluation index of historical turning operation, and the second information is real-time monitoring data; obtaining third information by quantum annealing processing according to the first information; obtaining fourth information by Kalman filtering processing according to the first information and the second information; obtaining fifth information by dynamic programming processing according to the third information and the fourth information; and obtaining sixth information by fuzzy logic reasoning processing according to the first information and the fifth information. Based on quantum annealing processing and dynamic programming processing, combined with graph construction, random forest algorithm and shortest path algorithm and other technologies, the application realizes intelligent design of the optimal control strategy of the turning operation, can automatically adjust the turning operation according to the real-time monitoring data and the turning effect evaluation index, and improves the turning efficiency and precision.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of power plant maintenance, in particular, to an automatic turning method and system thereof. BACKGROUND

[0002] With the rapid development of the power industry and the continuous progress of power unit technology, power units play a crucial role in the power generation process. During the operation and maintenance of the unit, turning is an important part of the maintenance, which directly affects the stability and performance of the unit. Turning is a precise adjustment process that requires precise measurement and adjustment of parameters such as runout, level, and air gap of each part of the unit. The existing turning method mainly relies on manual operation, and the turning process highly depends on the experience and skill level of the operator, which has the problems of complicated operation, low efficiency, and low precision, and is difficult to meet the needs of modern power industry for efficient and accurate maintenance.

[0003] Based on the above problems, there is an urgent need for an automatic turning method and system. SUMMARY

[0004] The purpose of the present application is to provide an automatic turning method, device, equipment and readable storage medium to improve the above problems. In order to achieve the above purpose, the technical scheme adopted by the present application is as follows:

[0005] In a first aspect, the present application provides an automatic turning method, comprising:

[0006] obtaining first information and second information, the first information being a sensor deployment scheme, sensor data and corresponding turning effect evaluation index of historical turning operation, and the second information being real-time monitoring data;

[0007] performing quantum annealing processing on the first information to obtain third information, the third information being a key feature and pattern recognition result of turning operation;

[0008] performing Kalman filtering processing on the first information and the second information to obtain fourth information, the fourth information being an estimated value of the current turning state;

[0009] performing dynamic programming processing on the third information and the fourth information to obtain fifth information, the fifth information being an optimal control strategy of turning operation;

[0010] performing fuzzy logic reasoning processing on the first information and the fifth information to obtain sixth information, the sixth information being a control parameter suitable for actual operation.

[0011] In a second aspect, the present application further provides an automatic turning system, comprising:

[0012] An acquisition module is configured to acquire first information and second information, the first information is a sensor deployment scheme, sensor data and corresponding swing effect evaluation indexes of historical swing operations, and the second information is real-time monitoring data;

[0013] An extraction module is configured to obtain third information by performing quantum annealing processing on the first information, the third information is key features and pattern recognition results of swing operations;

[0014] A prediction module is configured to obtain fourth information by performing Kalman filtering processing on the first information and the second information, the fourth information is an estimated value of a current swing state;

[0015] A planning module is configured to obtain fifth information by performing dynamic programming processing on the third information and the fourth information, the fifth information is an optimal control strategy of swing operations;

[0016] A reasoning module is configured to obtain sixth information by performing fuzzy logic reasoning processing on the first information and the fifth information, the sixth information is a control parameter suitable for actual operations.

[0017] The present application has the following advantages:

[0018] The present application realizes intelligent design of the optimal control strategy of swing operations based on quantum annealing processing and dynamic programming processing, combined with graph construction, random forest algorithm and shortest path algorithm, and can automatically adjust swing operations according to real-time monitoring data and swing effect evaluation indexes, thereby improving swing efficiency and accuracy.

[0019] Other features and advantages of the present application will be described in the following description, and some will become apparent from the description, or will be learned through practice of the application. The purpose and other advantages of the present application can be achieved and obtained by the structure specifically pointed out in the written description, claims and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0021] Figure 1 The automatic swing method flowchart described in the embodiments of the present application;

[0022] Figure 2 The swing system topology described in the embodiments of the present application. DETAILED DESCRIPTION

[0023] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some but not all of the embodiments of the present application. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0024] It should be noted that similar reference numerals and letters represent similar items in the following drawings, and therefore, once an item is defined in one drawing, it need not be further defined and explained in subsequent drawings. Meanwhile, in the description of the present application, the terms “first”, “second”, and the like are only used to distinguish description, and cannot be understood as indicating or implying relative importance.

[0025] Embodiment 1

[0026] The embodiment provides an automatic turning method.

[0027] Referring to Figure 1 , the method includes steps S100, S200, S300, S400 and S500.

[0028] The step S100 acquires first information and second information, the first information is a sensor deployment scheme, sensor data and corresponding turning effect evaluation index of historical turning operation, and the second information is real-time monitoring data.

[0029] It can be understood that the sensor deployment scheme, sensor data and corresponding turning effect evaluation index of historical turning operation cover information such as deviation of each section axis center, runout value and orientation. The deployment scheme of the sensor involves the installation position of each key part of the unit and the type of the sensor, and the sensor data is various parameters and state data obtained through the sensor, such as runout value, offset, etc. The corresponding turning effect evaluation index is calculated according to these data, such as runout, runout orientation, etc. The real-time monitoring data includes data obtained through the sensor in the turning process, which is mainly used for real-time monitoring of the state and parameter change of each part of the unit and the environmental condition. These data include the current runout, level, roundness and air gap of each part of the unit. Further, as shown in Figure 2 Figure 2 ​The topology of the turning gear system is shown, through which the integration and application of these data in the turning gear system can be intuitively understood. Specifically, the system is divided into three parts: data acquisition, data collection, data analysis and control. Data acquisition includes acquiring various sensor signals, such as turning gear signals of the air supply pipe, turning gear signals of the slip ring, turning gear signals of the upper guide, etc., responsible for monitoring the state of specific components. For example, the turning gear signal of the air supply pipe is related to the air supply system of the turbine, used to monitor and control the state of the air supply pipe during turning; the turning gear signal of the slip ring is used to monitor the position and state of the slip ring during turning; the turning gear signal of the upper guide focuses on the state of the upper guide bearing. Data collection devices, such as the upper guide turning gear data collection device, are responsible for collecting key parameters such as the roundness signals of the upper and lower end faces of the rotor and stator. These devices ensure the accuracy and real-time nature of the data, providing a basis for subsequent data analysis. The rotor upper end face roundness signal and the stator upper end face roundness signal are used to monitor the roundness of the upper end faces of the rotor and stator to ensure the balance and efficiency of the machine. The rotor lower end face roundness signal and the stator lower end face roundness signal monitor the roundness of the lower end faces of the rotor and stator, respectively. For data analysis and control, the turning gear data storage and analysis host is the core of this part, which processes and analyzes the data collected from the data collection devices. Through these data analysis, the turning control signal, including start, stop, speed control, etc., can be optimized to ensure the accuracy of the operation and the balance of the machine. The tooth disc position signal is used to monitor the precise position of the tooth disc, while the thrust head turning gear signal and the lower guide turning gear signal monitor the state of the thrust head and the lower guide bearing, respectively. The mirror plate turning gear signal is used to monitor the state of the mirror plate component. The lower wind tunnel turning gear data collection device and the water wheel chamber turning gear data collection device collect data in the lower wind tunnel area and the water wheel chamber during turning, respectively, while the water guide turning gear signal is related to the water guide bearing, used to monitor the state of the water guide bearing.

[0030] Step S200, performing quantum annealing processing on the first information to obtain third information, the third information being key features and pattern recognition results of the turning operation;

[0031] It should be noted that quantum annealing is an optimization algorithm that finds the global optimal solution by simulating the evolution of quantum states in an energy function. In this embodiment, the quantum annealing algorithm is applied to the processing of historical turning operation data to discover key features and patterns therein. These key features include the variation of parameters such as runout and offset of different parts of the unit, as well as data patterns and features under different turning modes.

[0032] Step S300, performing Kalman filtering processing on the first information and the second information to obtain fourth information, the fourth information being an estimated value of the current turning state;

[0033] It can be understood that Kalman filtering estimates the state of the system by continuously updating and fusing the measured data from the sensors and the predicted values of the system model. Through Kalman filtering processing in this step, the fourth information will provide an estimated value of the current turning gear state, including the swing, offset and other parameters of each part of the unit. These estimated values will have high accuracy and stability, which will help to monitor the changes and abnormal conditions in the turning process in real time, and provide important reference for subsequent decision and adjustment.

[0034] Step S400, according to the third information and the fourth information, a dynamic programming processing fifth information, the fifth information is the optimal control strategy of the turning operation;

[0035] It can be understood that dynamic programming is an optimization method for solving multi-stage decision problems, which selects the current optimal decision at each stage to ultimately achieve the global optimal solution. Through dynamic programming processing, the fifth information will provide the optimal control strategy of the turning operation, including the adjustment scheme, operation sequence and other parameters of each part of the unit. These strategies will be based on historical turning operation data and real-time monitoring data, combined with system model and prediction results, to maximize the turning effect, optimize the turning process, and meet specific turning requirements and constraints.

[0036] Step S500, according to the first information and the fifth information, a fuzzy logic reasoning processing is performed to obtain the sixth information, the sixth information is the control parameter suitable for actual operation.

[0037] It can be understood that fuzzy logic reasoning is a reasoning method based on fuzzy set theory, which is suitable for handling problems with strong uncertainty and fuzziness. Specifically, in this step, fuzzy logic reasoning will infer the control parameters suitable for the current turning operation according to the sensor deployment scheme and turning effect evaluation index in the historical data, as well as the adjustment scheme and operation sequence in the optimal control strategy. These control parameters involve the position adjustment of sensors, the optimization of operation sequence, the adjustment of turning effect evaluation index and other aspects. Through fuzzy logic reasoning processing, the sixth information will provide specific control parameters required for actual operation, which can be directly applied to the turning operation to achieve a more accurate, efficient and controllable turning process.

[0038] It should be noted that step S200 includes step S210, step S220, step S230 and step S240.

[0039] Step S210, according to the first information, a graph construction processing is performed to obtain the seventh information, the seventh information includes a set of vector graphs, the structure of each vector graph includes sensor nodes, sensor data attribute nodes, turning effect evaluation index attribute nodes, and the association relationship and spatial position relationship between sensors;

[0040] It can be understood that the sensor nodes can be represented as vertices or nodes in the graph, and each sensor corresponds to a node. The sensor data attribute node includes the data type collected by the sensor, data accuracy, etc. The disc effect evaluation index attribute node includes swing, offset, vibration, etc. The association relationship and spatial position relationship between sensors represent that there is a certain association or spatial position relationship between sensors, such as distance, angle, etc.

[0041] In step S220, the seventh information is input, a random forest algorithm is applied for feature selection and weight calculation, the eighth information is obtained by determining the importance of each feature and the influence degree on the disc effect, and the eighth information includes a feature weight set and feature importance information;

[0042] It should be noted that the random forest is an ensemble learning method that performs feature selection and prediction by constructing multiple decision trees, which has high accuracy and robustness. The specific steps include feature selection and feature weight calculation. In the feature selection stage, the algorithm will construct decision trees through multiple iterations, and determine which features have greater influence on the disc effect according to the best feature split at each node. In the feature weight calculation stage, the random forest algorithm calculates the weight of each feature according to the use and influence degree of each feature in multiple decision trees, reflecting the importance of each feature in the disc operation. The feature weight set and feature importance information obtained through this step provide a key reference for subsequent quantum annealing processing and fuzzy logic reasoning.

[0043] In step S230, data embedding processing is performed according to the seventh information and the eighth information, the feature weight set and the feature importance information are taken as the attributes of the nodes in the corresponding vector graph to obtain the ninth information.

[0044] This step aims to embed the feature weight and importance information into the node attributes of the vector graph to enrich the information content of the vector graph. Through such data embedding processing, each node can be assigned with feature weight and importance attributes related to the disc operation, so that the vector graph is more representative and information-rich.

[0045] In step S240, the ninth information is input, a quantum annealing algorithm is applied to optimize the graph, and the third information is obtained by simulating the evolution of quantum states in the energy function to find the global optimal solution.

[0046] Understandably, the quantum annealing algorithm treats the structure and node attributes of a vector diagram as the problem space, and seeks the state configuration that minimizes the energy function by adjusting the node states, thereby obtaining the optimal gantry operation strategy. During the optimization process, the algorithm considers the feature weights and importance information embedded in the node attributes to ensure that the selected operation strategy achieves the best gantry operation effect after comprehensively considering the weights and importance of various features. By simulating the evolution process of quantum states, the quantum annealing algorithm can search in the solution space of the problem and progressively optimize the state configuration of the vector diagram until it finds the globally optimal solution where the energy function is minimized.

[0047] It should be noted that step S240 includes steps S241, S242, S243 and S244.

[0048] Step S241: Based on the sensor deployment scheme and the corresponding turnaround effect evaluation index, the sensor deployment efficiency index is calculated using the graph-based shortest path algorithm.

[0049] This step calculates the sensor deployment efficiency index by applying a graph-based shortest path algorithm. This index helps evaluate the effectiveness and efficiency of sensor deployment, thereby guiding the optimization of turning gear operations. By calculating the sensor deployment efficiency index, the contribution and efficiency of each sensor deployment scheme in turning gear operations can be evaluated, thus providing guidance for optimizing sensor deployment. This will help improve the accuracy and efficiency of turning gear operations, thereby achieving better turning gear results. The formula for calculating the sensor deployment efficiency index is:

[0050] ;

[0051] in, This represents an indicator of sensor deployment efficiency. , Indicates the sensor's position number. Indicates important locations related to turning operations. This represents the set of all key parts. express Sensors to critical parts Path length, This represents the weight of the key component k. express Sensors and The distance between sensors express Sensors and The correlation weights between sensors.

[0052] Step S242: Based on the sensor deployment plan, the turning effect evaluation index, and the sensor deployment efficiency index, the energy function is obtained by function construction processing;

[0053] The energy function is:

[0054] ;

[0055] in, Represents the energy function. Indicates the number of sensors. Indicates the number of key parts. Indicates the number of evaluation indicators. Indicates the sensor's serial number. Indicates the serial number of the key part. Indicates the serial number of the evaluation indicator. Indicates the first The sensor to the first The path length of each key component Indicates the first Deployment efficiency metrics for individual sensors Indicates the first The sensor for the first The scores of each evaluation indicator.

[0056] Step S243: Perform quantum state simulation evolution processing based on the energy function to obtain the evolution process;

[0057] Understandably, quantum state simulation evolution is an optimization search method that utilizes quantum computing. Its main idea is to represent the state of a sensor deployment scheme as a quantum state and search for the optimal solution by simulating the evolution of this quantum state under the influence of an energy function. During the evolution process, quantum gate operations are used to adjust the state of the sensor deployment scheme in order to minimize the energy function.

[0058] Step S244: Solve the evolution process to obtain the global optimal solution of the energy function, and output the global optimal solution as the third information.

[0059] Preferably, an optimization algorithm, such as a genetic algorithm or particle swarm optimization, is used in this step to search for the global optimum. These algorithms continuously search for better solutions in the search space until a stopping condition is met or the global optimum is found. Specifically, during the algorithm's execution, the energy function value corresponding to each sensor deployment scheme is evaluated and compared to determine which scheme has the minimum energy function value. This process requires multiple iterations until the convergence condition is met. Finally, the sensor deployment scheme with the minimum energy function value is selected as the global optimum.

[0060] It should be noted that step S300 includes step S310, step S320, step S330 and step S340.

[0061] Step S310, according to the first information, the state space model of the turning gear system is constructed, the state space model includes the state variable, the state transition equation and the observation equation of the system, the state variable includes the swing, the level and the air gap parameter of each part of the unit;

[0062] Firstly, the state variables of the system need to be defined. In this embodiment, the state variables include the swing, the level and the air gap parameter of each part of the unit. These state variables describe the internal state of the system, such as the swing of the rotor and the stator of the unit and the gap between each part of the unit. Next, the state transition equation needs to be established. The state transition equation describes how the state of the system changes over time. In the turning gear system, the state transition equation is established based on physical laws and system dynamics principles, taking into account the interaction between each part of the unit during the turning process and the influence of external disturbances. Finally, the observation equation is determined, which describes the relationship between the system state and the observable data. In this step, real-time monitoring data obtained by sensors are used to establish the observation equation, and the estimated value of the turning gear system state is compared with the actual observation value, so as to verify the accuracy and reliability of the state space model. The establishment of this model can help the system to accurately grasp and effectively control its own state, and improve the safety and efficiency of the turning operation.

[0063] Step S320, according to the state transition equation of the state space model, the prediction processing is carried out, and the state of the system at the next time is predicted based on the current state and the dynamic properties of the system to obtain the prediction result;

[0064] It can be understood that the state transition equation describes how the state of the system evolves over time, so the future state can be predicted based on the current state and the dynamic characteristics of the system. The prediction result is the estimated value or predicted value of the system state, which provides important information about the future behavior of the system. These prediction results can be used to develop control strategies for turning operations, optimize system performance, or conduct risk assessments, etc. For example, based on the prediction result, the parameters of the turning operation can be adjusted or appropriate measures can be taken to deal with possible abnormal situations, thereby improving the stability and safety of the system. Through the prediction processing of this step, the behavior of the system can be better understood, potential problems can be found in time and appropriate measures can be taken for adjustment, thereby effectively improving the running efficiency and reliability of the turning system.

[0065] Step S330, according to the prediction result and the real-time monitoring data, the updating processing is carried out, the real-time monitoring data is connected with the state space by using the observation equation, and the system state is updated by Kalman filtering algorithm to obtain the updating result;

[0066] It can be understood that the real-time monitoring data is mapped into the state space through the observation equation, so as to be compared and adjusted with the predicted system state. Then, the predicted system state is fused with the real-time monitoring data by using the Kalman filtering algorithm, so as to obtain a more accurate estimation of the system state. The Kalman filtering algorithm can dynamically adjust the weights of the prediction result and the real-time monitoring data according to the dynamic properties of the system and the characteristics of the measurement noise, so as to realize the optimized estimation of the system state. Through the updating process, the prediction error can be corrected in time, so that the estimation of the system state is more accurate and reliable.

[0067] Step S340, data extraction processing is performed according to the updating result to obtain fourth information.

[0068] It can be understood that the latest estimation value of the system state can be obtained through the updating result, which contains information about the swing, level and air gap parameters of each part of the turning gear system. These information is crucial for understanding the current state of the turning gear system and the running condition of the system. In the data extraction processing, the part related to the required information is selected and extracted from the updated system state, which involves screening, converting or combining the state variables to obtain specific data forms.

[0069] It should be noted that step S400 includes step S410, step S420, step S430 and step S440.

[0070] Step S410, according to the third information and the fourth information, a state space and an action space are constructed, wherein the state space is used to represent the turning gear state, and the action space is used to represent the turning gear operation;

[0071] It can be understood that the state space is a collection of descriptions of the state of the turning gear system. In the state space, each state is a specific state that the system may be in. These states include various performance parameters of the turning gear system, environmental conditions and other factors affecting the behavior of the system. Using the updating result extracted from the fourth information, the system state can be represented as a vector containing various important parameters of the turning gear system, such as swing, level and air gap. The action space is a collection of descriptions of the turning gear operation. In the action space, each action is an operation or strategy that the system can perform. These actions include adjusting the turning gear parameters, changing the working mode or other operations affecting the system state. Using the optimal control strategy in the third information, the turning gear operation can be represented as an action set containing various operation modes that the system can take. By formalizing the state space and the action space, a foundation is provided for subsequent dynamic planning processing.

[0072] Step S420, according to the state space and action space, and combined with the motion law of the rotating part during the turning process, the force condition, and the influence degree of different turning operations on the system performance, a state transition model and a reward function are established, the state transition model is used to describe the probability distribution of the system transition to the next state under the given state and action, and the reward function is used to evaluate the advantages and disadvantages of each state action;

[0073] It can be understood that the establishment of the state transition model needs to understand the motion characteristics and force conditions of the turning system, and consider the influence of different operations on the system in different states. The actions in the turning system include adjusting the axis, changing the swing, adjusting the level, etc. Different operations may have different degrees of influence on the performance of the system. For example, adjusting the axis may change the stability of the system, and changing the swing may affect the efficiency of the system. Therefore, when establishing the state transition model, the influence of different operations on the system in different states needs to be considered, and these influences are included in the state transition probability. The reward function is defined according to the required performance indicators during the turning process, for example, the turning efficiency can be measured by minimizing energy loss or maximizing output power, and the stability can be evaluated by reducing the swing change. Further, by comprehensively considering the state transition model and the reward function, a reinforcement learning model can be established to select the optimal operation strategy under a given turning state. This model will be continuously optimized through learning historical data and interaction with the environment to achieve the optimization and performance improvement of the turning operation.

[0074] Step S430, based on the state transition model and the reward function, iterative optimization processing of the state value function is performed, the value function of each state is calculated in each iteration until the optimal solution is converged to obtain the optimized value function;

[0075] It should be noted that step S430 includes step S431, step S432, step S433, step S434, and step S435.

[0076] Step S431, the state value function is initialized to a suitable initial estimate.

[0077] Considering the characteristics and data of the turning system in this scenario, the initial estimate is determined according to the statistical characteristics of the historical turning data and real-time monitoring data to accurately reflect the current state of the system as much as possible.

[0078] Step S432, in each iteration, all possible states are traversed, and the value function of each state is calculated using the state transition model and the reward function.

[0079] This step combines the state transition model and the reward function to combine the expected return of each action with the probability of state transition, obtaining the value function of each state. This value function represents the expected return obtained by performing each action in the current state, helping to evaluate the pros and cons of each state.

[0080] Step S433, according to the update rule of dynamic programming, update the value function of each state according to Bellman equation.

[0081] This step considers the relationship and transition probability between states, as well as the expected return obtained by performing different operations. In the update process, the discount factor is also considered to balance the trade-off relationship between current reward and future reward.

[0082] Step S434, after each iteration, perform convergence check to check whether the difference between the current state value function and the value function of the last iteration is less than the pre-set threshold. If the convergence condition is met, stop iteration; otherwise, continue iteration.

[0083] This step aims to ensure that the state value function converges to the optimal solution, i.e. the maximum expected return that can be obtained by taking the optimal action in each state.

[0084] Step S435, during the iteration process, repeat the above steps until the state value function converges to the optimal solution. In this way, the optimal strategy of the system can be obtained to guide the disc operation, so as to maximize the performance of the system.

[0085] Step S440, according to the optimized value function, select the action that maximizes the value function as the optimal control strategy.

[0086] Through this process, the optimal disc operation strategy for the system can be determined. This strategy is based on the comprehensive search and evaluation of the system state space by the dynamic programming algorithm, as well as the analysis and optimization of the actions that can be taken in each state.

[0087] It should be noted that step S500 includes step S510, step S520, step S530 and step S540.

[0088] Step S510, according to the first information and the characteristics of the unit, perform fuzzy processing to construct fuzzy logic rules, which include the relationship between control parameters and disc operation characteristics;

[0089] Specifically, the fuzzy logic rules adopt an approach based on expert experience, and can also be learned from historical data using data mining and machine learning techniques. These rules will describe the degree of influence of different control parameters on the characteristics of the turning operation, and how to adjust these parameters in different situations to optimize the turning effect. Through this step, a fuzzy knowledge base can be established, which contains a wealth of relationships between control parameters and turning operation characteristics. This will provide a basis for subsequent fuzzy logic reasoning, enabling the system to automatically derive control parameters suitable for actual operation based on real-time monitoring data and unit characteristics, thereby achieving intelligent optimization of the turning operation.

[0090] Step S520, constructing a fuzzy reasoning mathematical model according to the fuzzy logic rules;

[0091] It can be understood that the fuzzy reasoning mathematical model is based on a fuzzy logic system, which includes fuzzy sets, fuzzy relations, and fuzzy reasoning rules. In this model, fuzzy sets will be used to describe the fuzzy information of real-time monitoring data and unit characteristics, fuzzy relations will be used to represent the relationships between different control parameters and turning operation characteristics, and fuzzy reasoning rules will be used to guide the reasoning process. Specifically, fuzzy sets are used to represent the fuzzy concepts of various monitoring indicators, such as "high", "low", "normal", etc. Then, through fuzzy relations, these fuzzy concepts are mapped to fuzzy values of control parameters to describe their relationships. Finally, using fuzzy reasoning rules, based on the conditions and conclusions defined in the fuzzy logic rules, reasoning is performed to determine the optimal control parameters. Through this step, a fuzzy reasoning mathematical model is established that can derive control parameters suitable for actual operation based on real-time monitoring data and unit characteristics.

[0092] Step S530, inputting the fifth information into the fuzzy reasoning mathematical model for fuzzy reasoning processing to obtain a reasoning result;

[0093] It can be understood that in the fuzzy reasoning process, the fuzzy reasoning system will perform fuzzy reasoning on the fuzzy input values according to the conditions and conclusions defined in the fuzzy logic rules, thereby producing fuzzy output values. These output values describe the degree of influence of different control parameters on the characteristics of the turning operation, and the recommended operation measures.

[0094] Step S540, defuzzification processing of the reasoning result, converting the fuzzy control parameters into actual operation parameters to obtain the sixth information.

[0095] It can be understood that the defuzzification process is the process of converting the fuzzy output results into clear and specific numerical values or instructions. In this step, the fuzzy control parameters are mapped to the actual operation parameters using the results of fuzzy reasoning and the pre-defined defuzzification rules. This process involves fuzzy set conversion, fuzzy set centroid calculation or other defuzzification methods to obtain the determined and accurate control parameters. The results of the defuzzification process will be provided to the control module of the system to guide the actual turning operation. These operation parameters can be specific control instructions, adjustment parameters or other operations to be performed to achieve the optimized turning effect.

[0096] It should be noted that step S520 includes step S521, step S522 and step S523.

[0097] Step S521, the fuzzy logic rules are converted and processed, and the mathematical expression of the fuzzy logic is obtained by converting the language description of each fuzzy rule into the mathematical expression of the fuzzy logic.

[0098] It can be understood that in the process of converting the natural language description of the fuzzy rule into the mathematical expression of the fuzzy logic, the input and output variables need to be defined, and the corresponding membership function needs to be selected; then, the keywords will be converted into logical operators and membership functions; the weight of each rule needs to be determined, which reflects its influence on the output result; at the same time, the logical conjunction word is determined to connect different conditions; finally, the converted rule is recorded in the rule base in the form of mathematical expression, which includes input and output variables, logical expression and weight information. This rule base provides a basis for subsequent fuzzy reasoning.

[0099] Step S522, according to the mathematical form rule base, the fuzzy reasoning mechanism is constructed by defining the membership function of the input and output variables and the logical rule between the fuzzy rules;

[0100] It can be understood that according to the fuzzy rules in the rule base, the logical relationship between the fuzzy rules is determined, and fuzzy logical operators (such as AND, OR, NOT, etc.) are usually used to connect different conditions. These logical rules determine how the fuzzy reasoning system derives the fuzzy value of the output variable according to the fuzzy value of the input variable. By establishing the fuzzy reasoning mechanism, the fuzzy value of the output variable can be derived according to the fuzzy value of the input variable and the rules defined in the fuzzy rule base, so as to realize the fuzzy reasoning process. This process allows the system to make decisions and inferences in the face of uncertainty and fuzziness, improving the adaptability and robustness of the system.

[0101] Step S523, according to the mathematical form rule base and the fuzzy reasoning mechanism, verification and optimization processing is carried out, and the fuzzy reasoning mathematical model is integrated.

[0102] It can be understood that the verification process includes checking the logical relationship of the fuzzy rules and adjusting and optimizing the parameters of the membership function, so that the fuzzy inference system can more accurately reflect the actual situation. The optimization methods include adjusting the weights and logical relationships of the fuzzy rules, optimizing the shape and parameters of the membership function, and increasing or decreasing the number of input variables and output variables. Through the verification and optimization process, a more accurate and reliable fuzzy inference mathematical model can be obtained, which can effectively handle the fuzziness and uncertainty of the input data and make inferences and decisions according to the pre-set rules and logical relationships, thereby providing more intelligent and reliable control parameters for the disc rotation operation.

[0103] Embodiment 2:

[0104] The embodiment provides an automatic disc rotation system, comprising:

[0105] An acquisition module is configured to acquire first information and second information, wherein the first information is a sensor deployment scheme, sensor data, and corresponding disc rotation effect evaluation indicators of historical disc rotation operations, and the second information is real-time monitoring data.

[0106] An extraction module is configured to perform quantum annealing processing on the first information to obtain third information, wherein the third information is key features and pattern recognition results of the disc rotation operation.

[0107] A prediction module is configured to perform Kalman filtering processing on the first information and the second information to obtain fourth information, wherein the fourth information is an estimated value of a current disc rotation state.

[0108] A planning module is configured to perform dynamic programming processing on the third information and the fourth information to obtain fifth information, wherein the fifth information is an optimal control strategy of the disc rotation operation.

[0109] An inference module is configured to perform fuzzy logic inference processing on the first information and the fifth information to obtain sixth information, wherein the sixth information is a control parameter suitable for actual operation.

[0110] In one specific embodiment of the present disclosure, the extraction module comprises:

[0111] A first construction unit is configured to perform graph construction processing on the first information to obtain seventh information, wherein the seventh information comprises a set of vector graphs, and the structure of each vector graph comprises sensor nodes, sensor data attribute nodes, disc rotation effect evaluation indicator attribute nodes, and association relationships and spatial position relationships between sensors.

[0112] The first computing unit is configured to apply a random forest algorithm to perform feature selection and weight calculation by taking the seventh information as input, to obtain eighth information by determining the importance of each feature and the degree of influence on the swing effect, and the eighth information includes a feature weight set and feature importance information;

[0113] The first embedding unit is configured to perform data embedding processing according to the seventh information and the eighth information, to obtain ninth information by taking the feature weight set and the feature importance information as the attributes of the nodes in the corresponding vector graph;

[0114] The first optimization unit is configured to apply a quantum annealing algorithm to perform optimization processing on the graph by taking the ninth information as input, to obtain the third information by simulating the evolution of a quantum state in an energy function to find a global optimal solution.

[0115] In one specific embodiment of the present disclosure, the first optimization unit includes:

[0116] The second computing unit is configured to calculate a sensor deployment efficiency indicator by using a graph-based shortest path algorithm according to the sensor deployment scheme and the corresponding swing effect evaluation indicator;

[0117] The second construction unit is configured to perform function construction processing to obtain an energy function according to the sensor deployment scheme, the swing effect evaluation indicator, and the sensor deployment efficiency indicator;

[0118] The first simulation unit is configured to perform quantum state simulation evolution processing to obtain an evolution process according to the energy function;

[0119] The first processing unit is configured to perform solving processing to obtain a global optimal solution of the energy function according to the evolution process, and to output the global optimal solution as the third information.

[0120] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An automatic jiggering method, characterized by, The application relates to a method for optimizing a disc wheel operation, and belongs to the technical field of disc wheel operation optimization. The method comprises the following steps: acquiring first information and second information, wherein the first information is a sensor deployment scheme of a historical disc wheel operation, sensor data and a corresponding disc wheel effect evaluation index, and the second information is real-time monitoring data; performing quantum annealing processing on the first information to obtain third information, wherein the third information is a key feature of the disc wheel operation and a mode recognition result; performing Kalman filtering processing on the first information and the second information to obtain fourth information, wherein the fourth information is an estimated value of a current disc wheel state; performing dynamic programming processing on the third information and the fourth information to obtain fifth information, wherein the fifth information is an optimal control strategy of the disc wheel operation; performing fuzzy logic reasoning processing on the first information and the fifth information to obtain sixth information, wherein the sixth information is a control parameter suitable for actual operation; performing quantum annealing processing on the first information to obtain third information, which comprises the following steps: performing graph construction processing on the first information to obtain seventh information, wherein the seventh information comprises a vector graph set, and the structure of each vector graph comprises a sensor node, a sensor data attribute node, a disc wheel effect evaluation index attribute node and the correlation and spatial position relationship between sensors; applying a random forest algorithm to perform feature selection and weight calculation by taking the seventh information as input, thereby obtaining eighth information, wherein the eighth information comprises a feature weight set and feature importance information; performing data embedding processing on the seventh information and the eighth information by taking the feature weight set and the feature importance information as attributes of nodes in the vector graph to obtain ninth information; applying quantum annealing algorithm to perform optimization processing on the graph by taking the ninth information as input, thereby simulating the evolution of a quantum state in an energy function to find a global optimal solution to obtain the third information; applying quantum annealing algorithm to perform optimization processing on the graph by taking the ninth information as input, thereby simulating the evolution of a quantum state in an energy function to find a global optimal solution to obtain the third information, which comprises the following steps: calculating a sensor deployment efficiency index by taking the sensor deployment scheme and the corresponding disc wheel effect evaluation index as input and applying a graph-based shortest path algorithm; constructing a function by taking the sensor deployment scheme, the disc wheel effect evaluation index and the sensor deployment efficiency index as input to obtain an energy function; performing quantum state simulation evolution processing on the energy function to obtain an evolution process; solving the energy function by taking the evolution process as input to obtain a global optimal solution, and outputting the global optimal solution as the third information; performing Kalman filtering processing on the first information and the second information to obtain fourth information, which comprises the following steps: constructing a state space model of a disc wheel system by taking the first information as input, wherein the state space model comprises state variables, a state transition equation and an observation equation of the system, and the state variables comprise swing, level and air gap parameters of each part of the unit; performing prediction processing on the state transition equation of the state space model to predict the state of the system at the next moment based on the current state and the dynamic property of the system to obtain a prediction result; According to the prediction result and the real-time monitoring data, an updating process is performed, the real-time monitoring data is associated with the state space by using the observation equation, and a system state is updated by using a Kalman filtering algorithm to obtain an updating result; According to the updating result, a data extraction process is performed to obtain fourth information.

2. The automatic derinding method according to claim 1, characterized in that, According to the third information and the fourth information, a dynamic programming process is performed to obtain fifth information, including: According to the third information and the fourth information, a state space and an action space are constructed, wherein the state space is used to represent a turning state, and the action space is used to represent a turning operation; According to the state space and the action space, and in combination with a motion law of a rotating component in a turning process, a force condition, and an influence degree of different turning operations on system performance, a state transition model and a reward function are established, the state transition model is used to describe a probability distribution of system transition to a next state under a given state and action, and the reward function is used to evaluate a degree of goodness of each state action; Based on the state transition model and the reward function, an iterative optimization process of a state value function is performed, a value function of each state is calculated in each iteration, and an optimal value function is obtained until a convergence to an optimal solution is achieved; According to the optimal value function, an action that maximizes the value function is selected as an optimal control strategy.

3. The automatic derinding method of claim 1, wherein, According to the fifth information, a fuzzy logic reasoning process is performed to obtain sixth information, including: According to the first information and unit characteristics, a fuzzy processing is performed to construct a fuzzy logic rule, the fuzzy logic rule includes a relationship between a control parameter and a turning operation feature; A fuzzy reasoning mathematical model is constructed according to the fuzzy logic rule; The fifth information is input into the fuzzy reasoning mathematical model to perform a fuzzy reasoning process to obtain a reasoning result; The reasoning result is de-fuzzied to convert the fuzzy control parameter into an actual operation parameter to obtain the sixth information.

4. The automatic derinding method according to claim 3, characterized in that, The fuzzy reasoning mathematical model is constructed according to the fuzzy logic rule, including: The fuzzy logic rule is converted to convert a language description of each fuzzy logic rule into a mathematical expression of fuzzy logic to obtain a mathematical form rule base of fuzzy logic; According to the mathematical form rule base, a fuzzy reasoning mechanism is established by defining membership functions of input variables and output variables and logical rules between fuzzy logic rules; According to the mathematical form rule base and the fuzzy reasoning mechanism, verification and optimization processes are performed to integrate a fuzzy reasoning mathematical model.

5. An automatic barring system characterized by, including: An acquisition module is configured to acquire first information and second information, the first information includes a sensor deployment scheme, sensor data, and a corresponding turning effect evaluation index of historical turning operations, and the second information includes real-time monitoring data; An extraction module is configured to perform a quantum annealing process on the first information to obtain third information, the third information includes key features and pattern recognition results of turning operations; A prediction module is configured to perform a Kalman filtering process on the first information and the second information to obtain fourth information, the fourth information includes an estimated value of a current turning state; The planning module is configured to perform dynamic programming on fifth information according to the third information and fourth information, the fifth information being an optimal control strategy of the turning operation; The reasoning module is configured to perform fuzzy logic reasoning on the first information and the fifth information to obtain sixth information, the sixth information being a control parameter applicable to actual operation; The extraction module comprises: The first construction unit is configured to perform graph construction on the first information to obtain seventh information, the seventh information comprising a set of vector graphs, a structure of each vector graph comprising a sensor node, a sensor data attribute node, a turning effect evaluation index attribute node, and an association relationship and a spatial position relationship between sensors; The first calculation unit is configured to take the seventh information as input, apply a random forest algorithm to perform feature selection and weight calculation, and obtain eighth information by determining the importance of each feature and the influence degree of the feature on the turning effect, the eighth information comprising a set of feature weights and feature importance information; The first embedding unit is configured to perform data embedding on the seventh information and the eighth information, take the set of feature weights and the feature importance information as attributes of nodes in the vector graph, and obtain ninth information; The first optimization unit is configured to take the ninth information as input, apply a quantum annealing algorithm to optimize the graph, and obtain the third information by simulating the evolution of a quantum state in an energy function to find a global optimal solution; The first optimization unit comprises: The second calculation unit is configured to calculate a sensor deployment efficiency index by using a graph-based shortest path algorithm according to the sensor deployment scheme and the corresponding turning effect evaluation index; The second construction unit is configured to perform function construction on the sensor deployment scheme, the turning effect evaluation index, and the sensor deployment efficiency index to obtain an energy function; The first simulation unit is configured to perform quantum state simulation evolution on the energy function to obtain an evolution process; The first processing unit is configured to perform solving on the evolution process to obtain a global optimal solution of the energy function, and output the global optimal solution as the third information.

Images