Axle full life cycle health management system

Abstract

The invention relates to axle management, in particular to an axle full-life-cycle health management system, which comprises a data acquisition unit for acquiring detection data of sensor groups mounted on an axle and transmitting the detection data to a background; the axle control management module is used for managing equipment information of each piece of equipment and supporting customized adjustment according to requirements; the data management module manages detection data of each device, analyzes device working condition information according to the detection data, generates a working condition report and sends the working condition report to a user; the fault prediction module is used for predicting equipment faults by adopting a quantum mouse fault prediction algorithm according to the detection data of each piece of equipment and sending fault early warning to a user; the maintenance suggestion module is used for generating corresponding maintenance suggestions according to the equipment working condition information and the fault prediction result and sending the maintenance suggestions to the user; according to the technical scheme provided by the invention, the defect that the axle fault is difficult to accurately and efficiently predict can be overcome.

Description

Technical Field

[0001] This invention relates to vehicle and axle management, and more specifically to a vehicle and axle full life cycle health management system. Background Technology

[0002] During operation, the health status of the axle directly affects the safety and reliability of vehicle operation. In the traditional model, the management of axles mainly relies on regular manual inspections and maintenance. This method not only consumes a lot of manpower and resources, but also makes it difficult to grasp the operating conditions of the axle in real time and accurately, and fails to detect potential faults in time. It is easy for a fault to occur and cause serious consequences, affecting the normal operation and safety of the vehicle.

[0003] With the development of sensor technology, it has become possible to install sensor arrays on vehicle axles to collect relevant data. However, how to effectively manage these collected detection data and extract valuable information from them to serve the health management of vehicle axles is a significant challenge.

[0004] Existing equipment management systems mostly only store data in a simple manner, failing to deeply analyze equipment operating conditions or generate intuitive reports for user reference. Furthermore, in terms of fault prediction, traditional algorithms often get stuck in local optima, significantly impacting the accuracy and timeliness of fault prediction and failing to provide reliable early warning information for axle maintenance. Moreover, the generation of maintenance recommendations often lacks scientific and reasonable basis and precise guidance, making it difficult to meet the needs of axle lifecycle health management. Therefore, a more advanced and comprehensive axle lifecycle health management system is urgently needed to solve these problems. Summary of the Invention

[0005] (a) Technical problems to be solved In view of the above-mentioned shortcomings of the existing technology, the present invention provides a vehicle axle full life cycle health management system, which can effectively overcome the defects of the existing technology in that it is difficult to accurately and efficiently predict vehicle axle failures.

[0006] (II) Technical Solution To achieve the above objectives, the present invention provides the following technical solution: The vehicle axle full life cycle health management system includes: The data acquisition unit collects detection data from various sensor groups installed on the axle and transmits it to the backend. The axle control and management module manages the equipment information of each device and supports customization and adjustment according to requirements; The data management module manages the testing data of each device, analyzes the device's operating condition information based on the testing data, and generates operating condition reports to send to the user. The fault prediction module uses the quantum lemming fault prediction algorithm to predict equipment faults based on the detection data of each device and sends fault warnings to users. The maintenance suggestion module generates corresponding maintenance suggestions based on equipment operating condition information and fault prediction results, and sends them to the user. Among them, the quantum lemming fault prediction algorithm includes: Quantum state encoding provides an initial state for the quantized migration of subsequent lemming populations, enhancing global search capabilities; Simulate the initial dispersion behavior of lemming populations based on the randomness of quantum states to avoid getting trapped in local optima; By using quantum gate operations to achieve continuous state updates, the lemming population is made to gather toward the global optimum, simulating the following behavior of lemmings and accelerating convergence to the global optimum. By introducing the quantum tunneling effect, individual lemmings are allowed to escape local optima with a certain probability, simulating the dispersed behavior of lemmings, improving global search capabilities, and avoiding getting trapped in local optima.

[0007] Preferably, the fault prediction module uses the quantum lemming fault prediction algorithm to predict equipment faults based on the detection data of each device, and sends fault warnings to the user, including: S1. Normalize the detection data of the sensor group to eliminate dimensional differences, and encode the normalized detection data into quantum states. The quantum state encoding provides the initial state for the subsequent quantum migration of the lemming population, thereby enhancing the global search capability. S2. Randomly generate an initial population of a certain size in the search space. Each lemming individual in the initial population represents a fault prediction solution. The quantum state of each lemming individual is represented by the superposition of multiple qubits. Simulate the initial dispersion behavior of the lemming population based on the randomness of the quantum state to avoid getting trapped in local optima. S3. Observe the current population, collapse the quantum state of the lemming individual into a classical solution, and calculate the fitness value of the lemming individual so as to guide the lemming individual to migrate to a higher-precision solution and optimize the search direction. S4. By using quantum gate operations to adjust the quantum state of individual lemmings, continuous state updates are achieved, causing the lemming population to converge toward the global optimum, simulating the following behavior of lemmings, and accelerating convergence to the global optimum. S5. Introducing the quantum tunneling effect allows individual lemmings to escape local optima with a certain probability, simulating the dispersed behavior of lemmings, breaking through the energy barrier of classical algorithms, improving global search capabilities, and avoiding getting trapped in local optima; S6. Calculate the fitness value of individual lemmings, record and update the global optimal solution; S7. Determine if the iteration termination condition is met. If the iteration termination condition is not met, return to S4. Otherwise, observe the final state of the population, output the fault type and predicted probability corresponding to the current global optimal solution, and send a fault warning to the user.

[0008] Preferably, in step S1, the detection data from the sensor array is normalized to eliminate dimensional differences, and the normalized detection data is encoded into quantum states. This quantum state encoding provides an initial state for the subsequent quantized migration of the lemming population, enhancing global search capabilities. This includes: The normalized detection data is encoded into quantum states using the following formula: ; Where, x i For the normalized detection data of the i-th sensor, Let x be the normalized detection data of the i-th sensor. i The corresponding single-qubit state, and This is the ground state for quantum computing.

[0009] Preferably, in S2, an initial population of a certain size is randomly generated within the search space. Each lemming individual in the initial population represents a fault prediction solution, and the quantum state of each lemming individual is represented by a superposition of multiple qubits. The initial dispersion behavior of the lemming population is simulated based on the randomness of the quantum state to avoid getting trapped in local optima, including: The quantum state of each lemming individual in the initial population is superimposed using the following formula: ; in, Let j be the quantum state of lemming individual. and The quantum state of lemming individual j The i-th single-qubit state The complex amplitudes together describe the state of the i-th single qubit. In state and The probability amplitude of the state determines the contribution weight of the detection data of the i-th sensor to the fault prediction solution. , Each as a determination , The initial reference value, when for the i-th single-qubit state During the measurement, the following was obtained: The probability of the state is ,get The probability of the state is ,and , The modulus of a complex number Let n represent the tensor product, and n be the number of sensors.

[0010] Preferably, in S3, the current population is observed, the quantum state of each lemming individual is collapsed into a classical solution, and the fitness value of each lemming individual is calculated to guide the lemming individual to migrate towards a higher-precision solution and optimize the search direction, including:

[0011] S31. Observe the current population and find the classical solution for collapsing the quantum state of an individual lemming into an n-bit binary string: ; in, The quantum state of lemming individual j The state collapses into the m-th classical solution X. m The probability, X represents the m-th classical solution. m Corresponding quantum computing ground state The quantum state of individual lemming j The inner product, i.e., extracting the m-th classical solution X. m Corresponding quantum computing ground state In the quantum state of lemming individual j The amplitude in X represents the m-th classical solution. m Corresponding quantum computing ground state In the quantum state of lemming individual j The square of the magnitude of the amplitude in the equation is used to calculate the m-th classical solution X. m Corresponding quantum computing ground state In the quantum state of lemming individual j Projection probability on; S32. Calculate the fitness value of individual lemmings based on the classical solution: ; Among them, F j Accuracy is the fitness value of lemming individual j. k The accuracy of historical fault prediction based on sensor detection data corresponding to a 1 in the k-th character of an n-bit binary string in the classical solution. Let K be the weight coefficient of the sensor corresponding to the k-th character being 1 in the n-bit binary string of the classical solution, where K is the number of 1 characters in the n-bit binary string of the classical solution, and K≤n.

[0012] Preferably, in S4, quantum gate operations are used to adjust the quantum states of individual lemmings to achieve continuous state updates, causing the lemming population to converge toward the global optimum, simulating the following behavior of lemmings, and accelerating convergence to the global optimum, including:

[0013] S41. Using a quantum rotation gate to adjust the state of each single qubit in the quantum state of an individual lemming: ; in, and For the i-th single-qubit state in the updated quantum state of lemming individual j The complex amplitude, and , This refers to a quantum rotating door. For rotation angle, t is the current iteration number. The attenuation rate, Used to balance global search and local development. This is the initial rotation angle; S42. Update the quantum state of individual lemmings to cause the lemming population to cluster toward the global optimum, simulating the following behavior of lemmings: ; in, Let be the quantum state of the updated lemming individual j.

[0014] Preferably, S5 introduces the quantum tunneling effect, allowing individual lemmings to escape local optima with a certain probability, simulating the dispersed behavior of lemmings, breaking through the energy barrier of classical algorithms, improving global search capabilities, and avoiding getting trapped in local optima, including: The tunneling probability, i.e., the probability that an individual lemming escapes the current local optimum, is calculated using the following formula to simulate the lemming's dispersion behavior: ; Among them, P j Let E be the tunneling probability of individual lemming j. j E best Let be the energy of lemming individual j and the energy of the current local optimum, respectively. The energy of a lemming individual is the reciprocal of its fitness value. The tunnel width is used to control the decay rate of the tunneling probability.

[0015] Preferably, in step S7, it is determined whether the iteration termination condition is met. If the iteration termination condition is not met, the process returns to step S4; otherwise, the final state of the population is observed, the fault type and predicted probability corresponding to the current global optimal solution are output, and a fault warning is sent to the user, including: S71. Determine whether the iteration termination condition is met. If the iteration termination condition is not met, return to S4; otherwise, proceed to S72. S72. Observe the final state of the population and output the fault type and predicted probability corresponding to the current global optimal solution: ; Among them, Pa Let be the predicted probability of type a fault. x represents the normalized detection data of the i-th sensor. i The corresponding single-qubit state The quantum state of the current global optimal solution. The squared magnitude of the amplitude in the data is used to calculate the normalized detection data x of the i-th sensor. i The corresponding single-qubit state The quantum state of the current global optimal solution. Projection probability on, x represents the normalized detection data of the i-th sensor. i Let A be the set of sensor detection data belonging to type a fault. a ; S73. The fault type with the highest predicted probability is used as the fault prediction result of the equipment, and a fault warning is sent to the user.

[0016] Preferably, the data acquisition unit and the sensor group are fixedly installed on each axle by threaded fasteners or welding. The sensor group includes a gear oil quality and temperature sensor, a gear oil level sensor, a load capacity sensor, and an axle housing vibration frequency sensor.

[0017] Preferably, the vehicle axle control management module manages the equipment information of each device, including the device number, product model, owner, and working status.

[0018] (III) Beneficial Effects Compared with the prior art, the vehicle axle full life cycle health management system provided by the present invention has the following beneficial effects: 1) Improve the accuracy of fault prediction and reduce the risk of misjudgment. The fault prediction module employs a quantum lemming fault prediction algorithm. This algorithm provides an initial state for the quantized migration of the lemming population through quantum state encoding, enhancing global search capabilities and comprehensively covering all possible operating conditions of the vehicle and axle. Based on the randomness of quantum states, it simulates the initial dispersion behavior of the lemming population, avoiding getting trapped in local optima and moving beyond judgments based solely on local data features. Quantum gate operations are used to achieve continuous state updates, causing the lemming population to converge towards the global optimum, simulating following behavior to accelerate convergence to the global optimum. The introduction of quantum tunneling allows individual lemmings to escape local optima and simulate dispersion behavior, further enhancing global search capabilities. This series of innovative mechanisms makes the algorithm's prediction of vehicle and axle faults more accurate, significantly reducing the probability of misjudgments and missed judgments, and providing a reliable guarantee for the stable operation of the vehicle and axle. 2) Enhance the real-time nature of fault prediction and prevent risks in a timely manner. The unique design of the quantum lemming fault prediction algorithm endows it with high computational efficiency and fast convergence characteristics. Based on the randomness of quantum states and the continuous state update of quantum gate operations, it can quickly process a large amount of real-time detection data collected by the sensor group, which can significantly shorten the prediction time of equipment faults. At the same time, the quantum tunneling effect allows individual lemmings to jump out of local optima, avoiding the computational delay caused by getting trapped in local optima, and ensuring that the system can send fault warnings to users in a timely manner. This real-time fault prediction capability allows users to take corresponding preventive measures before the fault occurs, effectively avoiding the expansion and deterioration of the fault, reducing economic losses and safety hazards. 3) Optimize the overall management efficiency of the system and improve overall benefits. The system also integrates a data acquisition unit, an axle control and management module, a data management module, and a maintenance suggestion module. The data acquisition unit collects detection data from the sensor array in real time and transmits it to the backend, providing rich data support for the system. The axle control and management module supports customized adjustments to meet the personalized management needs of different users. The data management module efficiently manages and analyzes the detection data and generates equipment status reports for users, enabling them to understand the axle's operating status in a timely manner. The maintenance suggestion module generates scientific and reasonable maintenance suggestions based on equipment status information and fault prediction results, helping users to formulate optimal maintenance plans. The collaborative work of these modules realizes intelligent and refined management of the entire axle lifecycle, reducing axle operating costs and improving overall economic efficiency. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of the system of the present invention; Figure 2 This is a schematic diagram of the process of predicting equipment failures using the quantum lemming fault prediction algorithm in this invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0022] The following describes the specific functional modules of the vehicle axle full life cycle health management system provided by this invention, using concrete examples (such as...). Figure 1 As shown in the figure, and considering the technical effects, the system functional modules include: The data acquisition unit collects detection data from various sensor groups installed on the axle and transmits it to the backend. The axle control and management module manages the equipment information of each device and supports customization and adjustment according to requirements; The data management module manages the testing data of each device, analyzes the device's operating condition information based on the testing data, and generates operating condition reports to send to the user. The fault prediction module uses the quantum lemming fault prediction algorithm to predict equipment faults based on the detection data of each device and sends fault warnings to users. The maintenance suggestion module generates corresponding maintenance suggestions based on equipment operating condition information and fault prediction results, and sends them to the user. Among them, the quantum lemming fault prediction algorithm includes: Quantum state encoding provides an initial state for the quantized migration of subsequent lemming populations, enhancing global search capabilities; Simulate the initial dispersion behavior of lemming populations based on the randomness of quantum states to avoid getting trapped in local optima; By using quantum gate operations to achieve continuous state updates, the lemming population is made to gather toward the global optimum, simulating the following behavior of lemmings and accelerating convergence to the global optimum. By introducing the quantum tunneling effect, individual lemmings are allowed to escape local optima with a certain probability, simulating the dispersed behavior of lemmings, improving global search capabilities, and avoiding getting trapped in local optima.

[0023] I. Fault Prediction Module The fault prediction module uses the quantum lemming fault prediction algorithm to predict equipment faults based on the detection data of each device, and sends fault warnings to the user, such as... Figure 2 As shown, it includes: 1) Normalize the detection data of the sensor group to eliminate dimensional differences, and encode the normalized detection data into quantum states. The quantum state encoding provides the initial state for the subsequent quantum migration of the lemming population, thereby enhancing the global search capability.

[0024] In the above steps, the normalized detection data is encoded into quantum states using the following formula: ; Where, x i For the normalized detection data of the i-th sensor, Let x be the normalized detection data of the i-th sensor. i The corresponding single-qubit state, and This is the ground state for quantum computing.

[0025] 2) Randomly generate an initial population of a certain size in the search space. Each lemming individual in the initial population represents a fault prediction solution. The quantum state of each lemming individual is represented by the superposition of multiple qubits. Based on the randomness of the quantum state, simulate the initial dispersion behavior of the lemming population to avoid getting trapped in local optima.

[0026] In the above steps, the quantum state of each lemming individual in the initial population is superimposed using the following formula: ;

[0027] in, Let j be the quantum state of lemming individual. and The quantum state of lemming individual j The i-th single-qubit state The complex amplitudes together describe the state of the i-th single qubit. In state and The probability amplitude of the state determines the contribution weight of the detection data of the i-th sensor to the fault prediction solution. , Each as a determination , The initial reference value, when for the i-th single-qubit state During the measurement, the following was obtained: The probability of the state is ,get The probability of the state is ,and , The modulus of a complex number Let n represent the tensor product, and n be the number of sensors.

[0028] 3) Observe the current population, collapse the quantum state of individual lemmings into classical solutions, and calculate the fitness value of individual lemmings in order to guide individual lemmings to migrate to higher-precision solutions and optimize the search direction.

[0029] The above steps include: The classical solution for observing the current population and collapsing the quantum state of an individual lemming into an n-bit binary string: ; in, The quantum state of lemming individual j The state collapses into the m-th classical solution X. m The probability, X represents the m-th classical solution. m Corresponding quantum computing ground state The quantum state of individual lemming j The inner product, i.e., extracting the m-th classical solution X. m Corresponding quantum computing ground state In the quantum state of lemming individual j The amplitude in X represents the m-th classical solution. m Corresponding quantum computing ground state In the quantum state of lemming individual j The square of the magnitude of the amplitude in the equation is used to calculate the m-th classical solution X. m Corresponding quantum computing ground state In the quantum state of lemming individual j Projection probability on; Calculate the fitness value of individual lemmings based on the classical solution: ; Among them, F j Accuracy is the fitness value of lemming individual j. k The accuracy of historical fault prediction based on sensor detection data corresponding to a 1 in the k-th character of an n-bit binary string in the classical solution. Let K be the weight coefficient of the sensor corresponding to the k-th character being 1 in the n-bit binary string of the classical solution, where K is the number of 1 characters in the n-bit binary string of the classical solution, and K≤n.

[0030] 4) By using quantum gate operations to adjust the quantum state of individual lemmings, continuous state updates are achieved, causing the lemming population to converge toward the global optimum, simulating the following behavior of lemmings, and accelerating convergence to the global optimum.

[0031] The above steps include:

[0032] Using quantum rotation gates to adjust the state of each single qubit in the quantum state of an individual lemming: ; in, and For the i-th single-qubit state in the updated quantum state of lemming individual j The complex amplitude, and , This refers to a quantum rotating door. For rotation angle, t is the current iteration number. The attenuation rate, Used to balance global search and local development. This is the initial rotation angle; Update the quantum state of individual lemmings to cause the lemming population to cluster toward the global optimum, simulating the following behavior of lemmings: ; in, Let be the quantum state of the updated lemming individual j.

[0033] 5) Introducing the quantum tunneling effect allows individual lemmings to escape local optima with a certain probability, simulating the dispersed behavior of lemmings, breaking through the energy barrier of classical algorithms, improving global search capabilities, and avoiding getting trapped in local optima.

[0034] In the above steps, the tunneling probability, i.e., the probability that an individual lemming escapes the current local optimum, is calculated using the following formula to simulate the lemming's dispersion behavior: ; Among them, P j Let E be the tunneling probability of individual lemming j. j E best Let be the energy of lemming individual j and the energy of the current local optimum, respectively. The energy of a lemming individual is the reciprocal of its fitness value. The tunnel width is used to control the decay rate of the tunneling probability.

[0035] 6) Calculate the fitness value of individual lemmings, record and update the global optimal solution.

[0036] 7) Determine if the iteration termination condition is met. If the iteration termination condition is not met, return to step 4. Otherwise, observe the final state of the population, output the fault type and predicted probability corresponding to the current global optimal solution, and send a fault warning to the user.

[0037] The above steps include: 1. Determine if the iteration termination condition is met. If the iteration termination condition is not met, return to step 4; otherwise, proceed to step 5. ;

[0038] Observe the final state of the population and output the fault type and predicted probability corresponding to the current global optimal solution: ;

[0039] Among them, P a Let be the predicted probability of type a fault. x represents the normalized detection data of the i-th sensor. i The corresponding single-qubit state The quantum state of the current global optimal solution. The squared magnitude of the amplitude in the data is used to calculate the normalized detection data x of the i-th sensor. i The corresponding single-qubit state The quantum state of the current global optimal solution. Projection probability on, x represents the normalized detection data of the i-th sensor. i Let A be the set of sensor detection data belonging to type a fault. a ; The fault type with the highest predicted probability is used as the fault prediction result of the equipment, and a fault warning is sent to the user.

[0040] The above technical solution, on the one hand, employs a quantum lemming fault prediction algorithm in the fault prediction module. This algorithm provides an initial state for the quantized migration of the lemming population through quantum state encoding, enhancing global search capabilities and comprehensively covering all possible operating conditions of the vehicle and axle. Based on the randomness of quantum states, it simulates the initial dispersion behavior of the lemming population, avoiding getting trapped in local optima and no longer limiting judgments to local data features. It utilizes quantum gate operations to achieve continuous state updates, causing the lemming population to converge towards the global optimum, simulating following behavior to accelerate convergence to the global optimum. Furthermore, it introduces the quantum tunneling effect, allowing individual lemmings to escape local optima and simulate dispersion behavior, further enhancing global search capabilities. This series of innovative mechanisms makes the algorithm more accurate in predicting vehicle and axle faults, significantly reducing the probability of misjudgments and missed judgments, and providing a reliable guarantee for the stable operation of the vehicle and axle. On the other hand, the unique design of the quantum lemming fault prediction algorithm endows it with efficient computing power and fast convergence characteristics. Based on the randomness of quantum states and the continuous state update of quantum gate operations, it can quickly process a large amount of real-time detection data collected by the sensor group, which can significantly shorten the prediction time of equipment faults. At the same time, the quantum tunneling effect allows individual lemmings to jump out of local optima, avoiding the computational delay caused by getting trapped in local optima, and ensuring that the system can send fault warnings to users in a timely manner. This real-time fault prediction capability allows users to take corresponding preventive measures before the fault occurs, effectively avoiding the expansion and deterioration of the fault, and reducing economic losses and safety hazards.

[0041] II. Data Acquisition Unit and Sensor Array The data acquisition unit and sensor group are fixedly installed on each axle by threaded fasteners or welding. The sensor group includes a gear oil quality and temperature sensor, a gear oil level sensor, a load capacity sensor, and an axle housing vibration frequency sensor.

[0042] III. Axle Control Management Module The vehicle axle control management module manages the equipment information of each device, including the device number, product model, owner, and working status.

[0043] In this application's technical solution, in addition to the fault prediction module, the vehicle axle full lifecycle health management system also integrates a data acquisition unit, a vehicle axle control management module, a data management module, and a maintenance suggestion module. The data acquisition unit collects real-time detection data from the sensor array and transmits it to the backend, providing rich data support for the system. The vehicle axle control management module supports customized adjustments based on requirements to meet the personalized management needs of different users. The data management module efficiently manages and analyzes the detection data and generates equipment condition reports, sending them to users so they can understand the vehicle axle's operating status in a timely manner. The maintenance suggestion module generates scientific and reasonable maintenance suggestions based on equipment condition information and fault prediction results, helping users formulate optimal maintenance plans. The collaborative work of these modules achieves intelligent and refined management of the entire vehicle axle lifecycle, reducing operating costs and improving overall economic efficiency.

[0044] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle axle full life cycle health management system, characterized by: include: The data acquisition unit collects detection data from various sensor groups installed on the axle and transmits it to the backend. The axle control and management module manages the equipment information of each device and supports customization and adjustment according to requirements; The data management module manages the testing data of each device, analyzes the device's operating condition information based on the testing data, and generates operating condition reports to send to the user. The fault prediction module uses the quantum lemming fault prediction algorithm to predict equipment faults based on the detection data of each device and sends fault warnings to users. The maintenance suggestion module generates corresponding maintenance suggestions based on equipment operating condition information and fault prediction results, and sends them to the user. Among them, the quantum lemming fault prediction algorithm includes: Quantum state encoding provides an initial state for the quantized migration of subsequent lemming populations, enhancing global search capabilities; Simulate the initial dispersion behavior of lemming populations based on the randomness of quantum states to avoid getting trapped in local optima; By using quantum gate operations to achieve continuous state updates, the lemming population is made to gather toward the global optimum, simulating the following behavior of lemmings and accelerating convergence to the global optimum. By introducing the quantum tunneling effect, individual lemmings are allowed to escape local optima with a certain probability, simulating the dispersed behavior of lemmings, improving global search capabilities, and avoiding getting trapped in local optima.

2. The vehicle axle full life cycle health management system according to claim 1, characterized in that: The fault prediction module uses the quantum lemming fault prediction algorithm to predict equipment faults based on the detection data of each device, and sends fault warnings to the user, including: S1. Normalize the detection data of the sensor group to eliminate dimensional differences, and encode the normalized detection data into quantum states. The quantum state encoding provides the initial state for the subsequent quantum migration of the lemming population, thereby enhancing the global search capability. S2. Randomly generate an initial population of a certain size in the search space. Each lemming individual in the initial population represents a fault prediction solution. The quantum state of each lemming individual is represented by the superposition of multiple qubits. Simulate the initial dispersion behavior of the lemming population based on the randomness of the quantum state to avoid getting trapped in local optima. S3. Observe the current population, collapse the quantum state of the lemming individual into a classical solution, and calculate the fitness value of the lemming individual so as to guide the lemming individual to migrate to a higher-precision solution and optimize the search direction. S4. By using quantum gate operations to adjust the quantum state of individual lemmings, continuous state updates are achieved, causing the lemming population to converge toward the global optimum, simulating the following behavior of lemmings, and accelerating convergence to the global optimum. S5. Introducing the quantum tunneling effect allows individual lemmings to escape local optima with a certain probability, simulating the dispersed behavior of lemmings, breaking through the energy barrier of classical algorithms, improving global search capabilities, and avoiding getting trapped in local optima; S6. Calculate the fitness value of individual lemmings, record and update the global optimal solution; S7. Determine if the iteration termination condition is met. If the iteration termination condition is not met, return to S4. Otherwise, observe the final state of the population, output the fault type and predicted probability corresponding to the current global optimal solution, and send a fault warning to the user.

3. The vehicle axle full life cycle health management system according to claim 2, characterized in that: In S1, the detection data from the sensor array is normalized to eliminate dimensional differences, and the normalized detection data is encoded into quantum states. This quantum state encoding provides the initial state for the subsequent quantized migration of the lemming population, enhancing global search capabilities, including: The normalized detection data is encoded into quantum states using the following formula: ； Where, x i For the normalized detection data of the i-th sensor, Let x be the normalized detection data of the i-th sensor. i The corresponding single-qubit state, and This is the ground state for quantum computing.

4. The vehicle axle full life cycle health management system according to claim 3, characterized in that: In S2, an initial population of a certain size is randomly generated within the search space. Each lemming individual in the initial population represents a fault prediction solution, and the quantum state of each lemming individual is represented by a superposition of multiple qubits. Based on the randomness of the quantum state, the initial dispersion behavior of the lemming population is simulated to avoid getting trapped in local optima, including: The quantum state of each lemming individual in the initial population is superimposed using the following formula: ； in, Let j be the quantum state of lemming individual. and The quantum state of lemming individual j The i-th single-qubit state The complex amplitudes together describe the state of the i-th single qubit. In state and The probability amplitude of the state determines the contribution weight of the detection data of the i-th sensor to the fault prediction solution. , Each as a determination , The initial reference value, when for the i-th single-qubit state During the measurement, the following was obtained: The probability of the state is ,get The probability of the state is ,and , The modulus of a complex number Let n represent the tensor product, and n be the number of sensors.

5. The vehicle axle full life cycle health management system according to claim 4, characterized in that: In S3, the current population is observed, the quantum states of individual lemmings are collapsed into classical solutions, and the fitness values ​​of individual lemmings are calculated to guide them towards higher-precision solutions and optimize the search direction, including: S31. Observe the current population and find the classical solution for collapsing the quantum state of an individual lemming into an n-bit binary string: ； in, The quantum state of lemming individual j The state collapses into the m-th classical solution X. m The probability, X represents the m-th classical solution. m Corresponding quantum computing ground state The quantum state of individual lemming j The inner product, i.e., extracting the m-th classical solution X. m Corresponding quantum computing ground state In the quantum state of lemming individual j The amplitude in X represents the m-th classical solution. m Corresponding quantum computing ground state In the quantum state of lemming individual j The square of the magnitude of the amplitude in the equation is used to calculate the m-th classical solution X. m Corresponding quantum computing ground state In the quantum state of lemming individual j Projection probability on; S32. Calculate the fitness value of individual lemmings based on the classical solution: ； Among them, F j Accuracy is the fitness value of lemming individual j. k The accuracy of historical fault prediction based on sensor detection data corresponding to a 1 in the k-th character of an n-bit binary string in the classical solution. Let K be the weight coefficient of the sensor corresponding to the k-th character being 1 in the n-bit binary string of the classical solution, where K is the number of 1 characters in the n-bit binary string of the classical solution, and K≤n.

6. The vehicle axle full life cycle health management system according to claim 5, characterized in that: In S4, quantum gate operations are used to adjust the quantum states of individual lemmings, achieving continuous state updates and causing the lemming population to converge toward the global optimum. This simulates the following behavior of lemmings and accelerates convergence to the global optimum, including: S41. Using a quantum rotation gate to adjust the state of each single qubit in the quantum state of an individual lemming: ； in, and For the i-th single-qubit state in the updated quantum state of lemming individual j The complex amplitude, and , This refers to a quantum rotating door. For rotation angle, t is the current iteration number. The attenuation rate, Used to balance global search and local development. This is the initial rotation angle; S42. Update the quantum state of individual lemmings to cause the lemming population to cluster toward the global optimum, simulating the following behavior of lemmings: ； in, Let be the quantum state of the updated lemming individual j.

7. The vehicle axle full life cycle health management system according to claim 6, characterized in that: S5 introduces the quantum tunneling effect, allowing lemmings to escape local optima with a certain probability. This simulates the dispersed behavior of lemmings, overcomes the energy barrier of classical algorithms, improves global search capabilities, and avoids getting trapped in local optima, including: The tunneling probability, i.e., the probability that an individual lemming escapes the current local optimum, is calculated using the following formula to simulate the lemming's dispersion behavior: ； Among them, P j Let E be the tunneling probability of individual lemming j. j E best Let be the energy of lemming individual j and the energy of the current local optimum, respectively. The energy of a lemming individual is the reciprocal of its fitness value. The tunnel width is used to control the decay rate of the tunneling probability.

8. The vehicle axle full life cycle health management system according to claim 7, characterized in that: In S7, it checks whether the iteration termination condition is met. If the termination condition is not met, it returns to S4; otherwise, it observes the final state of the population, outputs the fault type and predicted probability corresponding to the current global optimal solution, and sends a fault warning to the user, including: S71. Determine whether the iteration termination condition is met. If the iteration termination condition is not met, return to S4; otherwise, proceed to S72. S72. Observe the final state of the population and output the fault type and predicted probability corresponding to the current global optimal solution: ； Among them, P a Let be the predicted probability of type a fault. x represents the normalized detection data of the i-th sensor. i The corresponding single-qubit state The quantum state of the current global optimal solution. The squared magnitude of the amplitude in the data is used to calculate the normalized detection data x of the i-th sensor. i The corresponding single-qubit state The quantum state of the current global optimal solution. Projection probability on, x represents the normalized detection data of the i-th sensor. i Let A be the set of sensor detection data belonging to type a fault. a ; S73. The fault type with the highest predicted probability is used as the fault prediction result of the equipment, and a fault warning is sent to the user.

9. The vehicle axle full life cycle health management system according to claim 1, characterized in that: The data acquisition unit and sensor group are fixedly installed on each axle by threaded fasteners or welding. The sensor group includes a gear oil quality and temperature sensor, a gear oil level sensor, a load capacity sensor, and an axle housing vibration frequency sensor.

10. The vehicle axle full life cycle health management system according to claim 1, characterized in that: The vehicle axle control and management module manages the equipment information of each device, including the device number, product model, owner, and working status.

Images