Online health monitoring and repairing execution system for mining locomotive

Abstract

The invention relates to an online health monitoring and repairing execution system for a mining locomotive, and belongs to the technical field of health monitoring of mining locomotives. The system comprises a data online acquisition module which is used for online acquiring various standard state data of each part of a target mining locomotive in real time; the model construction module is used for constructing a target three-dimensional model of the target mining locomotive; the information generation module is used for generating state information of the target three-dimensional model; the real-time health monitoring module is used for calculating the real-time health degree of each component at the current moment according to the state information; the service life prediction module is used for predicting the residual service life of each part according to the state information; and the repair execution module is used for calculating the repair level of each part according to the real-time health degree and the residual life of each part to repair each part. According to the method, the accuracy, the timeliness and the efficiency of monitoring and repairing the health of the mining locomotive are improved, the resource allocation is optimized, and the fault risk of the target mining locomotive is reduced.

Description

Technical Field

[0001] This invention relates to the field of mine locomotive health monitoring technology, and in particular to an online health monitoring and repair system for mine locomotives. Background Technology

[0002] As a core component of the mining transportation system, the operating status of mining locomotives directly affects the mine's production efficiency and safety level. Mining locomotives typically operate in harsh environments, such as high temperatures, humidity, dust, and vibration, which can easily lead to component damage and malfunctions over long periods. With the deepening of smart mine construction, the demand for intelligent operation and maintenance of mining locomotives is becoming increasingly urgent.

[0003] Currently, the health monitoring and maintenance of mining locomotives relies on traditional manual inspection methods. In this model, workers need to conduct regular or irregular on-site inspections of the mining locomotives to check the operating status and potential faults of various components. Manual inspections primarily rely on workers' senses, such as sight, hearing, and touch, to assess the health of the locomotive's components.

[0004] While manual inspections can uncover some significant problems, they suffer from limitations such as low efficiency, susceptibility to human error, and inability to provide real-time monitoring. Inspectors typically work during specific time periods, and their ability to anticipate mine locomotive malfunctions is poor, making it difficult to promptly identify potential problems or minor faults. This results in components failing after a considerable period of time, increasing the complexity and cost of mine locomotive repairs and reducing repair efficiency. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides an online health monitoring and repair execution system for mining locomotives. The technical solution of this invention is as follows: A mining locomotive online health monitoring and repair execution system includes: The online data acquisition module is used to acquire various raw state data of each component of the target mining locomotive in real time, and to preprocess the raw state data to obtain various standard state data of each component. The model building module is used to build a basic three-dimensional model of the target mining locomotive and map multiple standard state data of each component into the basic three-dimensional model to obtain the target three-dimensional model of the target mining locomotive. The information generation module is used to generate the status information of the target 3D model based on the various standard status data of each component and the attribute information of the target mining locomotive. The real-time health monitoring module is used to calculate the real-time health status of each component based on the status information, and to configure the real-time health status of each component in the target 3D model; The life prediction module is used to predict the remaining life of each component based on the status information and to configure the remaining life of each component in the target 3D model. The repair execution module is used to calculate the repair level of each component based on its real-time health and remaining lifespan, and then repair each component according to the repair level of all components.

[0006] Preferably, the online data acquisition module includes: The data acquisition unit is used to collect various raw state data of each component through various types of sensors pre-configured for each component of the target mining locomotive; The wireless transmission unit is used to acquire multiple raw state data of each component through wireless transmission, and to time-align each type of raw state data of all components to obtain multiple standard state data of each component.

[0007] Preferably, the model building module includes: The basic 3D model building unit is used to obtain the basic information of each component of the target mining locomotive, and to build a component 3D model of each component based on the basic information of each component. Based on the structure of the target mining locomotive, the component 3D models of each component are connected to obtain the basic 3D model of the target mining locomotive. The mapping unit is used to map multiple standard state data of each component to the component's 3D model; The integration unit is used to integrate the 3D model of each component and its various standard state data into the basic 3D model to obtain the target 3D model of the target mining locomotive.

[0008] Preferably, the real-time health monitoring module includes: The real-time data acquisition unit is used to acquire each standard state data of each component at the current moment based on the state information, and use it as the real-time state data of each component. The real-time health calculation unit is used to calculate the entropy health value of the target component through each real-time status data of the target component, and to calculate the real-time health of the target component at the current moment based on the entropy health value, wherein the target component is any component in the target three-dimensional model; Configuration unit, used to configure real-time health for each component in the target 3D model.

[0009] Preferably, the real-time health calculation unit includes: The matrix construction sub-unit is used to construct a real-time matrix based on each real-time status data of the target component, and to construct a comparison vector based on the preset standard value corresponding to each real-time status data. The distance calculation subunit is used to input the real-time matrix and the comparison vector into the phase space and calculate the Mahalanobis distance between each real-time state data in the real-time matrix and the comparison vector. The entropy health value calculation subunit is used to calculate the q-entropy of each real-time state data based on the Mahalanobis distance between each real-time state data and the comparison vector, and to normalize the q-entropy of all real-time state data to obtain the state entropy health value of each real-time state data. The health calculation subunit is used to superimpose the state entropy health values ​​of all real-time status data of the target component to obtain the entropy health value of the target component at the current moment. The preset health conversion coefficient is multiplied by the entropy health value of the target component at the current moment to obtain the real-time health of the target component.

[0010] Preferably, the lifetime prediction module includes: The data acquisition unit is used to acquire the standard lifespan of each component and various standard status data from the start of use to the current time based on the status information, and to use the various standard status data from the start of use to the current time as various historical status data. The life prediction unit is used to construct the spatiotemporal matrix of each component based on its standard life and various historical state data, and predict the remaining life of each component based on the spatiotemporal matrix. Lifetime configuration unit, used to configure the remaining lifetime for each component in the target 3D model.

[0011] Preferably, the life prediction unit, when predicting the remaining life of each component based on a spatiotemporal matrix, includes: Calculate the eigenvectors of the spatiotemporal matrix for each component; The fatigue strength curve of each component is constructed based on the feature vector, where the horizontal axis of the fatigue strength curve is fatigue time and the vertical axis is fatigue strength. The fatigue strength of each component is obtained from the fatigue strength curve for each future time period. The remaining life of each component is calculated based on the preset stress amplitude, material constant, and fatigue strength for each future time period.

[0012] Preferably, the repair execution module includes: The repair impact coefficient calculation unit is used to calculate the repair impact coefficient of each component based on various real-time status data of each component; The repair level calculation unit is used to calculate the repair level of each component based on its real-time health, remaining lifespan, and repair impact coefficient. The strategy generation unit is used to identify components with a repair level greater than the repair threshold as components to be repaired, and to sort and repair each component according to its repair level.

[0013] Preferably, the repair impact coefficient calculation unit includes: The state vector construction sub-unit is used to construct a state vector based on various real-time state data of each component; The distance calculation subunit is used to calculate the average vector distance between each real-time state data of each component and the state vector; The Repair Impact Coefficient sub-unit is used to probabilistically convert the average vector distance of each component to obtain the repair impact coefficient of each component.

[0014] Preferably, when calculating the remaining life N of the component based on the preset stress amplitude, material constant, and fatigue strength of any component in future time periods, it is achieved through formula (1): (1); In formula (1), Ci represents the fatigue intensity in the i-th time period in the future. The sum of fatigue strength over all future time periods is represented by S, which represents the preset stress amplitude of the component, and m represents the material constant of the component.

[0015] All of the above-mentioned optional technical solutions can be combined arbitrarily, and the present invention will not provide a detailed description of the structure after each combination.

[0016] By means of the above solution, the beneficial effects of the present invention are as follows: The target 3D model of the target mining locomotive is constructed by the model building module. The structure and status information of the target mining locomotive can be intuitively displayed through the target 3D model, providing clear and accurate status information of the target mining locomotive. The real-time health monitoring module calculates the real-time health status of each component of the target mining locomotive at the current moment, and the lifespan prediction module predicts the remaining lifespan of the target components. After configuring the real-time health status and lifespan of each component in the target 3D model, the repair execution module calculates the repair level of each component based on its real-time health status and remaining lifespan and performs repairs accordingly. This achieves the goal of combining the real-time health status and remaining lifespan of each component of the target mining locomotive to determine the repair level of each component at the current moment, providing a comprehensive solution for the health management of the target mining locomotive. Further integration of the real-time health status and remaining lifespan of each component of the target mining locomotive with the target 3D model will make the entire online health monitoring and repair execution process more intelligent and visualized. This will not only effectively improve the accuracy, timeliness, and efficiency of repair strategies, but also optimize resource allocation, reduce the failure risk of the target mining locomotive, and extend the service life of components. It will produce significant beneficial effects in improving production efficiency and reducing operation and maintenance costs, and will also solve the limitations of manual inspections caused by human interference and the inability to monitor in real time.

[0017] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the structure of an online health monitoring and repair execution system for mining locomotives provided in an embodiment of the present invention. Detailed Implementation

[0019] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0020] like Figure 1 As shown, this embodiment of the invention provides an online health monitoring and repair execution system for mining locomotives, comprising: The online data acquisition module is used to acquire various raw state data of each component of the target mining locomotive in real time, and to preprocess the raw state data to obtain various standard state data of each component. The model building module is used to build a basic three-dimensional model of the target mining locomotive and map multiple standard state data of each component into the basic three-dimensional model to obtain the target three-dimensional model of the target mining locomotive. The information generation module is used to generate the status information of the target 3D model based on the various standard status data of each component and the attribute information of the target mining locomotive. The real-time health monitoring module is used to calculate the real-time health status of each component based on the status information, and to configure the real-time health status of each component in the target 3D model; The life prediction module is used to predict the remaining life of each component based on the status information and to configure the remaining life of each component in the target 3D model. The repair execution module is used to calculate the repair level of each component based on its real-time health and remaining lifespan, and then repair each component according to the repair level of all components.

[0021] Specifically, in the online data acquisition module, the target mining locomotive refers to a locomotive used in underground or open-pit mining environments such as mines, shafts, and mining areas to complete transportation tasks. In this embodiment of the invention, it serves as the research target for online health monitoring and repair. The components of the target mining locomotive include starting components (engine), transmission components, braking components (brake discs), power supply components (battery), and hydraulic components (hydraulic pump), etc. The raw state data includes types such as temperature, pressure, speed, friction, and voltage. When preprocessing the raw state data, it is standardized using the z-score method to transform the raw state data into a fixed range (such as between 0 and 1), and the standardized state data is obtained.

[0022] In the model building module, the basic 3D model of the target mining locomotive is a 3D digital representation model constructed based on the various components and overall geometric structure of the target mining locomotive. When mapping multiple standard state data of each component to the basic 3D model, the multiple standard state data of each component are directly bound to the corresponding component model in the basic 3D model and then visualized.

[0023] In the information generation module, the attribute information of the target mining locomotive includes the standard lifespan of each component, the preset stress amplitude and material constants of each component, the unique identifier of the target mining locomotive, and the structure and connection relationships of the target mining locomotive. The state information of the target 3D model includes multiple standard state data for each component and the attribute information of the target mining locomotive.

[0024] In the real-time health monitoring module, the real-time health score of a component is a metric used to represent the component's current working status and health condition. After configuring the real-time health score for each component in the target 3D model, the value of each component's real-time health score will be displayed in the target 3D model using different colors. For example, red indicates that the corresponding component's real-time health score is less than 30, and green indicates that the corresponding component's real-time health score is greater than 80.

[0025] In the life prediction module, remaining life refers to the estimated time that each component of the target mining locomotive can continue to operate normally without failure or damage. Specifically, after configuring the remaining life for a component in the target 3D model, the remaining life of that component will be visualized in the target 3D model.

[0026] In the repair execution module, the repair level refers to a quantitative value that assesses the urgency of repairing the components of the target mining locomotive that have been damaged or worn during use. It is generally divided into three repair levels: low, medium, and high.

[0027] In one specific embodiment, the online data acquisition module includes: The data acquisition unit is used to collect various raw state data of each component through various types of sensors pre-configured for each component of the target mining locomotive; The wireless transmission unit is used to acquire multiple raw state data of each component through wireless transmission, and to time-align each type of raw state data of all components to obtain multiple standard state data of each component.

[0028] Specifically, the data acquisition unit includes sensor types such as temperature sensors, pressure sensors, speed sensors, and current sensors; the raw state data includes types such as temperature, pressure, speed, and current.

[0029] In the wireless transmission unit, wireless transmission methods include Wi-Fi, Bluetooth, and cellular networks. When time-aligning the raw state data of all components, the various raw state data of all components are first standardized. Then, all standardized raw state data are time-aligned according to a pre-set time reference. It should be noted that for standardized raw state data with a sampling frequency lower than the time reference, linear interpolation is performed to obtain the standard state data for that standardized raw state data.

[0030] In one specific embodiment, the model building module includes: The basic 3D model building unit is used to obtain the basic information of each component of the target mining locomotive, and to build a component 3D model of each component based on the basic information of each component. Based on the structure of the target mining locomotive, the component 3D models of each component are connected to obtain the basic 3D model of the target mining locomotive. The mapping unit is used to map multiple standard state data of each component to the component's 3D model; The integration unit is used to integrate the 3D model of each component and its various standard state data into the basic 3D model to obtain the target 3D model of the target mining locomotive.

[0031] Specifically, the basic 3D model building unit includes fundamental information such as geometric dimensions, shape features, structural features, assembly methods, and connection methods. When acquiring the fundamental information for each component, it is based on the composition structure of the target mining locomotive and the manufacturing information of each component. When generating the 3D model of each component, the fundamental information of each component is input into a 3D model building tool, which then outputs the 3D model of each component. These 3D model building tools include SolidWorks, AutoCAD, PTC Creo, and Catia. When connecting the 3D models of each component, an assembly tool is used to align multiple 3D models according to the actual connection method. For example, in SolidWorks, the "Mate" function can be used to align different components according to constraints such as hole positions, faces, and edges to obtain the fundamental 3D model of the target mining locomotive.

[0032] In the mapping unit, when mapping multiple standard state data of each component to the component's 3D model, the correspondence between the standard state data of each component and its 3D model is established to facilitate subsequent integration.

[0033] In the integration unit, integration refers to simultaneously loading the 3D model of each component and its standard state data into the basic 3D model of the target mining locomotive to form a complete and integrated target 3D model.

[0034] In one specific embodiment, the real-time health monitoring module includes: The real-time data acquisition unit is used to acquire each standard state data of each component at the current moment based on the state information, and use it as the real-time state data of each component. The real-time health calculation unit is used to calculate the entropy health value of the target component through each real-time status data of the target component, and to calculate the real-time health of the target component at the current moment based on the entropy health value, wherein the target component is any component in the target three-dimensional model; Configuration unit, used to configure real-time health for each component in the target 3D model.

[0035] Specifically, in the real-time data acquisition unit, the real-time status data is the standard status data of the component at the current moment. The standard status data includes both real-time status data and historical status data.

[0036] In the real-time health calculation unit, the entropy health value is an indicator based on entropy theory to evaluate the health of each component. The higher the entropy health value of a component, the more chaotic its state and the worse its health; conversely, the lower the entropy health value, the more stable its state and the better its health. The real-time health value changes in the opposite direction to the entropy health value; the higher the real-time health value, the better the health of the component.

[0037] After configuring the real-time health status of each component in the target 3D model, the configuration unit can display the real-time health status in the target 3D model in real time, realizing a real-time and intuitive display of the real-time health status of each component.

[0038] In one specific embodiment, the real-time health calculation unit includes: The matrix construction sub-unit is used to construct a real-time matrix based on each real-time status data of the target component, and to construct a comparison vector based on the preset standard value corresponding to each real-time status data. The distance calculation subunit is used to input the real-time matrix and the comparison vector into the phase space and calculate the Mahalanobis distance between each real-time state data in the real-time matrix and the comparison vector. The entropy health value calculation subunit is used to calculate the q-entropy of each real-time state data based on the Mahalanobis distance between each real-time state data and the comparison vector, and to normalize the q-entropy of all real-time state data to obtain the state entropy health value of each real-time state data. The health calculation subunit is used to superimpose the state entropy health values ​​of all real-time status data of the target component to obtain the entropy health value of the target component at the current moment. The preset health conversion coefficient is multiplied by the entropy health value of the target component at the current moment to obtain the real-time health of the target component.

[0039] Specifically, in the matrix construction sub-unit, each row of the real-time matrix represents a component, and each column represents a type of real-time status data; each element of the comparison vector represents a preset standard value of that type of real-time status data corresponding to the order of the real-time status data in each column of the real-time matrix. The preset standard values ​​are determined empirically.

[0040] In the distance calculation subunit, the phase space is a multi-dimensional space, where each dimension represents a type of real-time state data. By mapping various real-time state data of the target component to preset standard values ​​in the phase space, different aspects of the real-time state data in various dimensions can be highlighted. Mahalanobis distance is a distance metric method for measuring the similarity between data points. When calculating the Mahalanobis distance D between a certain type of real-time state data x and the comparison vector u, it can be achieved through formula (2): In formula (2), T represents transpose. Let (xu) be the inverse matrix of the covariance matrix formed by the standard state data corresponding to each real-time state data position, and let (xu) be the matrix formed by the real-time state data and the comparison vector.

[0041] In the entropy health value calculation subunit, when calculating the q-entropy H of a certain real-time state data based on the Mahalanobis distance D between a certain real-time state data and the comparison vector, it is achieved through formula (3): (3); In formula (3), q represents the adjustment coefficient, ln() represents the logarithmic function, and D q This represents the Mahalanobis distance raised to the power of q.

[0042] In the health calculation sub-unit, the preset health conversion coefficient is a conversion coefficient determined based on historical experience values.

[0043] In one specific embodiment, the lifetime prediction module includes: The data acquisition unit is used to acquire the standard lifespan of each component and various standard status data from the start of use to the current time based on the status information, and to use the various standard status data from the start of use to the current time as various historical status data. The life prediction unit is used to construct the spatiotemporal matrix of each component based on its standard life and various historical state data, and predict the remaining life of each component based on the spatiotemporal matrix. Lifetime configuration unit, used to configure the remaining lifetime for each component in the target 3D model.

[0044] Specifically, in the data acquisition unit, the data acquired during the operation of a component is the various standard state data from the time a component starts using the data to the current time, excluding data that is not in operation.

[0045] In a lifespan prediction unit, a spatiotemporal matrix is ​​a structured data representation used to integrate the standard lifespan and historical state data of each component with the time dimension. In the spatiotemporal matrix of a specific component, each row represents multiple historical state data at a given time point, and each column represents the same historical state data at the corresponding time point. The standard lifespan of the component is placed at the end of each row of the spatiotemporal matrix. For example, the spatiotemporal matrix of a specific component can be represented as follows: .

[0046] When configuring the remaining lifetime for each component in the target 3D model, the lifetime configuration unit establishes a mapping relationship between the remaining lifetime of each component and the corresponding 3D model of the component, and binds the remaining lifetime of each component to the corresponding 3D model of the component according to the mapping relationship. For example, the remaining lifetime of a component is displayed next to its component 3D model and shown as: remaining lifetime 30 days.

[0047] In one specific embodiment, the lifetime prediction unit, when predicting the remaining lifetime of each component based on a spatiotemporal matrix, includes: Calculate the eigenvectors of the spatiotemporal matrix for each component; The fatigue strength curve of each component is constructed based on the feature vector, where the horizontal axis of the fatigue strength curve is fatigue time and the vertical axis is fatigue strength. The fatigue strength of each component is obtained from the fatigue strength curve for each future time period. The remaining life of each component is calculated based on the preset stress amplitude, material constant, and fatigue strength for each future time period.

[0048] Specifically, the eigenvector calculation of the spatiotemporal matrix is ​​achieved by performing statistical analysis on each column of the spatiotemporal matrix to obtain the statistical characteristics of the historical state data at each time point. The statistical characteristics of the historical state data at each time point are then concatenated according to the order of the historical state data categories in the spatiotemporal matrix to obtain the eigenvector of the spatiotemporal matrix.

[0049] When calculating the remaining life of a component, a fatigue strength function for a known time period is first constructed based on the component's preset stress amplitude and a publicly available fatigue strength formula. Then, the fatigue strength function for the known time period is fitted with the characteristics of each time point in the component's historical state data from its feature vector, resulting in a fatigue strength curve. The division of time periods on the horizontal axis of the fatigue strength curve is determined based on the component's fatigue condition during historical operation. Finally, the remaining life of the component is calculated based on its preset stress amplitude, material constants, and fatigue strength for each future time period.

[0050] The fatigue strength function of a certain component can be expressed by formula (5): (5); In formula (5), C represents the fatigue strength of the component, f represents the fatigue strength coefficient of the component, S represents the preset stress amplitude of the component, NF represents the number of working cycles of the component, and RD represents the working cycle coefficient. During fitting, the historical state data of each time node and its features and working cycle coefficient in the feature vector are fitted to obtain the fatigue strength curve.

[0051] In addition, the preset stress amplitude of a component is a pre-set stress level value for that component; the material constant of a component is a specific numerical parameter determined in advance based on empirical values ​​to describe the material properties of that component in terms of fatigue, strength, toughness, hardness, etc.

[0052] In one specific embodiment, the repair execution module includes: The repair impact coefficient calculation unit is used to calculate the repair impact coefficient of each component based on various real-time status data of each component; The repair level calculation unit is used to calculate the repair level of each component based on its real-time health, remaining lifespan, and repair impact coefficient. The strategy generation unit is used to identify components with a repair level greater than the repair threshold as components to be repaired, and to sort and repair each component according to its repair level.

[0053] Specifically, in the repair impact coefficient calculation unit, the repair impact coefficient is a parameter that measures the relationship between component status and repair requirements, and is used to evaluate the impact of real-time component status data on the repair level.

[0054] In the repair level calculation unit, the calculation method for calculating the repair level of each component is: real-time health × repair impact coefficient + (1 - repair impact coefficient) × remaining lifespan.

[0055] The strategy generation unit has a repair threshold that is a minimum threshold determined based on empirical values ​​to indicate whether repair is needed.

[0056] In one specific embodiment, the repair impact coefficient calculation unit includes: The state vector construction sub-unit is used to construct a state vector based on various real-time state data of each component; The distance calculation subunit is used to calculate the average vector distance between each real-time state data of each component and the state vector; The Repair Impact Coefficient sub-unit is used to probabilistically convert the average vector distance of each component to obtain the repair impact coefficient of each component.

[0057] Specifically, in the state vector construction sub-unit, multiple real-time state data of a certain component are generated into a state vector in a predetermined order. For example, the three real-time state data of a certain component are: temperature 38, pressure 500 and speed 200. The state vector constructed based on these three real-time state data is [38, 500, 200].

[0058] In the distance calculation sub-unit, when calculating the average vector distance of a certain component, the average vector distance between all real-time state data of the component and the state vector is taken. The vector distance between each type of real-time state data of each component and the state vector is calculated using the cosine similarity formula.

[0059] In the sub-unit of the repair influence coefficient, the average vector distance of each component is probabilistically represented by an exponential function, as shown in formula (4): (4); In formula (4), R represents the repair impact coefficient of a certain component, avg(d) represents the average vector distance of the component, exp() represents the exponential function, and b represents the adjustment factor, which is obtained by calculating the standard deviation of the vector distance between each real-time state data of the component and the state vector.

[0060] In a specific embodiment, when calculating the remaining life N of a component based on its preset stress amplitude, material constant, and fatigue strength over future time periods, the calculation is performed using formula (1): (1); In formula (1), Ci represents the fatigue intensity in the i-th time period in the future. The sum of fatigue strength over all future time periods is represented by S, which represents the preset stress amplitude of the component, and m represents the material constant of the component.

[0061] Specifically, formula (1) describes the remaining life of the component by linearizing the cumulative material damage of the component.

[0062] Based on all the above embodiments, the online health monitoring and repair execution system for mining locomotives provided by the present invention has the following beneficial effects: First, the online data acquisition module acquires and preprocesses various raw state data of each component of the target mining locomotive, obtaining various standard state data of each component, which provides an accurate and diverse data foundation for subsequent health status assessment and life assessment of the target mining locomotive.

[0063] Next, the model building module maps the various standard state data of each component to the basic 3D model to obtain the target 3D model of the target mining locomotive. The real-time status of each component of the target mining locomotive can be visualized and displayed intuitively through the target 3D model, which facilitates the intuitive acquisition of the real-time status of the target mining locomotive and improves the convenience of visualizing the health assessment results of each component in the future.

[0064] Then, the real-time health monitoring module calculates the real-time health status of each component based on the status information and configures the real-time health status of each component in the target 3D model. Similarly, the lifespan prediction module predicts the remaining lifespan of each component based on the status information and configures the remaining lifespan of each component in the target 3D model. This enables real-time determination of the health status and remaining lifespan of each component of the target mining locomotive, facilitating the rapid and accurate identification of the location of real-time anomalies and potential risks in the target mining locomotive, and improving the accuracy and effectiveness of repairs. By configuring the real-time health status and remaining lifespan of each component in the target 3D model, the real-time health status and remaining lifespan are visualized. Monitoring and managing each component through the target 3D model becomes more intuitive and operable, greatly improving management efficiency and decision-making speed.

[0065] Finally, by combining the real-time health and remaining lifespan of each component with the repair execution module, the repair level of each component is calculated, and each component is repaired. This enables predictive repair based on the real-time health and remaining lifespan of each component, effectively improving the accuracy and timeliness of the repair strategy and optimizing resource allocation.

[0066] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A mining locomotive online health monitoring and repair execution system, characterized in that, include: The online data acquisition module is used to acquire various raw state data of each component of the target mining locomotive in real time, and to preprocess the raw state data to obtain various standard state data of each component. The model building module is used to build a basic three-dimensional model of the target mining locomotive and map multiple standard state data of each component into the basic three-dimensional model to obtain the target three-dimensional model of the target mining locomotive. The information generation module is used to generate the status information of the target 3D model based on the various standard status data of each component and the attribute information of the target mining locomotive. The real-time health monitoring module is used to calculate the real-time health status of each component based on the status information, and to configure the real-time health status of each component in the target 3D model; The life prediction module is used to predict the remaining life of each component based on the status information and to configure the remaining life of each component in the target 3D model. The repair execution module is used to calculate the repair level of each component based on its real-time health and remaining lifespan, and then repair each component according to the repair level of all components.

2. The online health monitoring and repair execution system for mining locomotives according to claim 1, characterized in that, The online data acquisition module includes: The data acquisition unit is used to collect various raw state data of each component through various types of sensors pre-configured for each component of the target mining locomotive; The wireless transmission unit is used to acquire multiple raw state data of each component through wireless transmission, and to time-align each type of raw state data of all components to obtain multiple standard state data of each component.

3. The online health monitoring and repair execution system for mining locomotives according to claim 1, characterized in that, The model building module includes: The basic 3D model building unit is used to obtain the basic information of each component of the target mining locomotive, and to build a component 3D model of each component based on the basic information of each component. Based on the structure of the target mining locomotive, the component 3D models of each component are connected to obtain the basic 3D model of the target mining locomotive. The mapping unit is used to map multiple standard state data of each component to the component's 3D model; The integration unit is used to integrate the 3D model of each component and its various standard state data into the basic 3D model to obtain the target 3D model of the target mining locomotive.

4. The online health monitoring and repair execution system for mining locomotives according to claim 1, characterized in that, The real-time health monitoring module includes: The real-time data acquisition unit is used to acquire each standard state data of each component at the current moment based on the state information, and use it as the real-time state data of each component. The real-time health calculation unit is used to calculate the entropy health value of the target component through each real-time status data of the target component, and to calculate the real-time health of the target component at the current moment based on the entropy health value, wherein the target component is any component in the target three-dimensional model; Configuration unit, used to configure real-time health for each component in the target 3D model.

5. The online health monitoring and repair execution system for mining locomotives according to claim 4, characterized in that, The real-time health calculation unit includes: The matrix construction sub-unit is used to construct a real-time matrix based on each real-time status data of the target component, and to construct a comparison vector based on the preset standard value corresponding to each real-time status data. The distance calculation subunit is used to input the real-time matrix and the comparison vector into the phase space and calculate the Mahalanobis distance between each real-time state data in the real-time matrix and the comparison vector. The entropy health value calculation subunit is used to calculate the q-entropy of each real-time state data based on the Mahalanobis distance between each real-time state data and the comparison vector, and to normalize the q-entropy of all real-time state data to obtain the state entropy health value of each real-time state data. The health calculation subunit is used to superimpose the state entropy health values ​​of all real-time status data of the target component to obtain the entropy health value of the target component at the current moment. The preset health conversion coefficient is multiplied by the entropy health value of the target component at the current moment to obtain the real-time health of the target component.

6. The online health monitoring and repair execution system for mining locomotives according to claim 1, characterized in that, The lifetime prediction module includes: The data acquisition unit is used to acquire the standard lifespan of each component and various standard status data from the start of use to the current time based on the status information, and to use the various standard status data from the start of use to the current time as various historical status data. The life prediction unit is used to construct the spatiotemporal matrix of each component based on its standard life and various historical state data, and predict the remaining life of each component based on the spatiotemporal matrix. Lifetime configuration unit, used to configure the remaining lifetime for each component in the target 3D model.

7. The online health monitoring and repair execution system for mining locomotives according to claim 6, characterized in that, The lifetime prediction unit, when predicting the remaining lifetime of each component based on the spatiotemporal matrix, includes: Calculate the eigenvectors of the spatiotemporal matrix for each component; The fatigue strength curve of each component is constructed based on the feature vector, where the horizontal axis of the fatigue strength curve is fatigue time and the vertical axis is fatigue strength. The fatigue strength of each component is obtained from the fatigue strength curve for each future time period. The remaining life of each component is calculated based on the preset stress amplitude, material constant, and fatigue strength for each future time period.

8. The online health monitoring and repair execution system for mining locomotives according to claim 4, characterized in that, The repair execution module includes: The repair impact coefficient calculation unit is used to calculate the repair impact coefficient of each component based on various real-time status data of each component; The repair level calculation unit is used to calculate the repair level of each component based on its real-time health, remaining lifespan, and repair impact coefficient. The strategy generation unit is used to identify components with a repair level greater than the repair threshold as components to be repaired, and to sort and repair each component according to its repair level.

9. The online health monitoring and repair execution system for mining locomotives according to claim 8, characterized in that, The repair impact coefficient calculation unit includes: The state vector construction sub-unit is used to construct a state vector based on various real-time state data of each component; The distance calculation subunit is used to calculate the average vector distance between each real-time state data of each component and the state vector; The Repair Impact Coefficient sub-unit is used to probabilistically convert the average vector distance of each component to obtain the repair impact coefficient of each component.

10. The online health monitoring and repair execution system for mining locomotives according to claim 7, characterized in that, When calculating the remaining life N of a component based on its preset stress amplitude, material constant, and fatigue strength over future time periods, the calculation is performed using formula (1): （1）； In formula (1), Ci represents the fatigue intensity in the i-th time period in the future. The sum of fatigue strength over all future time periods is represented by S, which represents the preset stress amplitude of the component, and m represents the material constant of the component.

Images