A mine locomotive online health monitoring and repair execution system

Abstract

The present application relates to a kind of mining locomotive online health monitoring and repair execution system, belong to mining locomotive health monitoring technical field.System includes: data online acquisition module, for real-time online acquisition target mining locomotive each component multiple standard state data;Model construction module, for constructing the target three-dimensional model of target mining locomotive;Information generation module, for generating the state information of target three-dimensional model;Real-time health monitoring module, for calculating the real-time health degree of each component according to state information;Life prediction module, for predicting the residual life of each component according to state information;Repair execution module, for calculating the repair grade of each component according to the real-time health degree and residual life of each component, and repairing each component.The present application improves the precision, timeliness and efficiency of mining locomotive health monitoring and repair, optimizes resource allocation, and reduces the failure risk of target mining locomotive.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of health monitoring of mine locomotives, and particularly relates to an online health monitoring and repair execution system for mine locomotives. BACKGROUND

[0002] As a core component of the mine transportation system, the operation state of the mine locomotive directly affects the production efficiency and safety level of the mine. The mine locomotive usually works in harsh environments, such as high temperature, humidity, dust, vibration, etc. Long-term operation can easily cause damage and failure of components. With the deepening of the construction of smart mines, the intelligent operation and maintenance demand of mine locomotives is increasingly urgent.

[0003] At present, the health monitoring and maintenance of mine locomotives rely on traditional manual inspection mode. In this mode, the workers need to periodically or irregularly check the mine locomotive on site to detect the operation state and potential failure of each component of the mine locomotive. Manual inspection mainly relies on the worker's vision, hearing and touch to judge the health of each component of the mine locomotive.

[0004] Although the manual inspection mode can find some obvious problems, it has the limitations of low efficiency, easy to be disturbed by artificial factors, and unable to monitor in real time. The working time of the inspection personnel is usually concentrated in certain time periods, and the predictability of the mine locomotive failure is poor, which is difficult to find potential hidden dangers or minor failures in time. When the components of the mine locomotive fail, it has accumulated hidden dangers for a long time, increasing the complexity and cost of the repair of the mine locomotive and reducing the efficiency of the repair. SUMMARY

[0005] To solve the above technical problems, the present application provides an online health monitoring and repair execution system for mine locomotives. The technical scheme of the present application is as follows:

[0006] An online health monitoring and repair execution system for mine locomotives, comprising:

[0007] A data online acquisition module for acquiring in real time a plurality of original state data of each component of a target mine locomotive, and preprocessing the original state data to obtain a plurality of standard state data of each component;

[0008] A model construction module for constructing a basic three-dimensional model of the target mine locomotive, and mapping the plurality of standard state data of each component into the basic three-dimensional model to obtain a target three-dimensional model of the target mine locomotive;

[0009] An information generation module for generating state information of the target three-dimensional model according to the plurality of standard state data of each component and the attribute information of the target mine locomotive;

[0010] a real-time health monitoring module configured to calculate a real-time health degree of each component at a current time according to the state information, and configure the real-time health degree of each component in the target three-dimensional model;

[0011] a life prediction module configured to predict a remaining life of each component according to the state information, and configure the remaining life of each component in the target three-dimensional model;

[0012] a repair execution module configured to calculate a repair level of each component according to the real-time health degree and the remaining life of each component, and repair each component according to the repair level of all components.

[0013] Preferably, the data online acquisition module comprises:

[0014] a data acquisition unit configured to acquire a plurality of original state data of each component through a plurality of types of sensors pre-configured for each component of the target mine vehicle;

[0015] a wireless transmission unit configured to acquire the plurality of original state data of each component through a wireless transmission mode, and time-align each original state data of all components to obtain a plurality of standard state data of each component.

[0016] Preferably, the model construction module comprises:

[0017] a basic three-dimensional model construction unit configured to acquire basic information of each component of the target mine vehicle, construct a component three-dimensional model of each component according to the basic information of each component, and connect the component three-dimensional models of each component based on the structure of the target mine vehicle to obtain a basic three-dimensional model of the target mine vehicle;

[0018] a mapping unit configured to map the plurality of standard state data of each component to the component three-dimensional model of each component;

[0019] an integration unit configured to integrate the component three-dimensional model of each component and the plurality of standard state data of each component into the basic three-dimensional model to obtain the target three-dimensional model of the target mine vehicle.

[0020] Preferably, the real-time health monitoring module comprises:

[0021] a real-time data acquisition unit configured to acquire each standard state data of each component at a current time according to the state information as each real-time state data of each component;

[0022] a real-time health degree calculation unit configured to calculate an entropy health value of a target component through each real-time state data of the target component, and calculate a real-time health degree of the target component at a current time according to the entropy health value, wherein the target component is any component in the target three-dimensional model;

[0023] The configuration unit is configured to configure a real-time health degree for each component in the target three-dimensional model.

[0024] Preferably, the real-time health degree calculation unit comprises:

[0025] A matrix construction subunit is configured to construct a real-time matrix according to each real-time state data of the target component, and construct a comparison vector according to a preset standard value corresponding to each real-time state data;

[0026] A distance calculation subunit is configured to input the real-time matrix and the comparison vector into a phase space, and calculate Mahalanobis distance between each real-time state data in the real-time matrix and the comparison vector;

[0027] An entropy health value calculation subunit is configured to calculate q-entropy of each real-time state data according to the Mahalanobis distance between each real-time state data and the comparison vector, and normalize the q-entropy of all real-time state data to obtain a state entropy health value of each real-time state data;

[0028] A health degree calculation subunit is configured to superimpose the state entropy health values of all real-time state data of the target component to obtain an entropy health value of the target component at a current time, multiply a preset health conversion coefficient with the entropy health value of the target component at the current time, and obtain a real-time health degree of the target component.

[0029] Preferably, the life prediction module comprises:

[0030] A data acquisition unit is configured to acquire a standard life of each component and a plurality of standard state data from a start time to a current time according to state information, and take the plurality of standard state data from the start time to the current time as a plurality of historical state data;

[0031] A life prediction unit is configured to construct a space-time matrix of each component according to the standard life of each component and the plurality of historical state data of each component, and predict a remaining life of each component based on the space-time matrix;

[0032] A life configuration unit is configured to configure a remaining life for each component in the target three-dimensional model.

[0033] Preferably, the life prediction unit comprises the following when predicting the remaining life of each component based on the space-time matrix:

[0034] Calculate a feature vector of the space-time matrix of each component;

[0035] Construct a fatigue strength curve of each component according to the feature vector, wherein an abscissa of the fatigue strength curve is fatigue time and an ordinate of the fatigue strength curve is fatigue strength;

[0036] According to the fatigue strength curve, fatigue strength of each component in each time period in the future is obtained, and according to the preset stress amplitude, material constant and fatigue strength of each component in each time period in the future, the residual life of each component is calculated.

[0037] Preferably, the repair execution module comprises:

[0038] A repair influence coefficient calculation unit is configured to calculate a repair influence coefficient of each component according to the plurality of real-time state data of each component;

[0039] A repair level calculation unit is configured to calculate a repair level of each component according to the real-time health degree, residual life and repair influence coefficient of each component;

[0040] A strategy generation unit is configured to take the components with the repair level greater than the repair threshold as components to be repaired, and to repair each component to be repaired according to the size of the repair level of each component to be repaired.

[0041] Preferably, the repair influence coefficient calculation unit comprises:

[0042] A state vector construction subunit is configured to construct a state vector according to the plurality of real-time state data of each component;

[0043] A distance calculation subunit is configured to calculate an average vector distance between each real-time state data of each component and the state vector;

[0044] A repair influence coefficient subunit is configured to probabilize the average vector distance of each component to obtain the repair influence coefficient of each component.

[0045] Preferably, when the residual life N of any component is calculated according to the preset stress amplitude, material constant and fatigue strength of the component in each time period in the future, it is realized by formula (1):

[0046] (1);

[0047] In formula (1), Ci represents the fatigue strength in the i th time period in the future, represents the sum of the fatigue strength of all time periods in the future, S represents the preset stress amplitude of the component, and m represents the material constant of the component.

[0048] All the optional technical solutions described above can be combined arbitrarily, and the application does not describe the structures after combination in detail.

[0049] Through the above-mentioned solutions, the application has the following beneficial effects:

[0050] The target three-dimensional model of the target mine locomotive is constructed through the model construction module, the structure and state information of the target mine locomotive can be intuitively displayed through the target three-dimensional model, and clear and accurate state information of the target mine locomotive is provided;

[0051] The real-time health monitoring module is used for calculating the real-time health degree of each component of the target mine locomotive at the current time, the life prediction module is used for predicting the remaining life of the target component, and after the real-time health degree and the remaining life of each component are configured in the target three-dimensional model, the repair execution module calculates the repair level of each component according to the real-time health degree and the remaining life of each component and performs repair, so that the real-time health degree and the remaining life of each component of the target mine locomotive are combined to judge the repair level of each component of the target mine locomotive at the current time, a comprehensive solution for health management of the target mine locomotive is provided, the real-time health degree and the remaining life of each component of the target mine locomotive are combined with the target three-dimensional model, the process of online health monitoring and repair execution is more intelligent and visual, not only the accuracy, timeliness and efficiency of the repair strategy can be effectively improved, but also the resource allocation can be optimized, the failure risk of the target mine locomotive is reduced, the service life of the component is prolonged, remarkable beneficial effects in improving production efficiency and reducing operation and maintenance cost are produced, and the problems of artificial interference and real-time monitoring limitation caused by artificial inspection can be solved.

[0052] The above description is only a summary of the technical scheme of the present application, in order to more clearly understand the technical means of the present application and can be implemented according to the content of the description, the following will be described in detail with the preferred embodiments of the present application and the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0053] Figure 1 It is a structure schematic diagram of a mine locomotive online health monitoring and repair execution system provided by the embodiment of the present application. DETAILED DESCRIPTION

[0054] The specific embodiments of the present application will be further described in detail below in combination with the drawings and examples. The following examples are used to illustrate the present application, but not to limit the scope of the present application.

[0055] As Figure 1 shown, the embodiment of the present application provides a mine locomotive online health monitoring and repair execution system, which comprises:

[0056] The data online acquisition module is used for acquiring a plurality of original state data of each component of the target mine locomotive in real time, and pre-processing the original state data to obtain a plurality of standard state data of each component;

[0057] a model construction module, configured to construct a basic three-dimensional model of the target mine locomotive and map the multiple standard state data of each component into the basic three-dimensional model to obtain a target three-dimensional model of the target mine locomotive;

[0058] an information generation module, configured to generate state information of the target three-dimensional model according to the multiple standard state data of each component and attribute information of the target mine locomotive;

[0059] a real-time health monitoring module, configured to calculate a real-time health degree of each component at a current time according to the state information and configure the real-time health degree for each component in the target three-dimensional model;

[0060] a life prediction module, configured to predict a remaining life of each component according to the state information and configure the remaining life for each component in the target three-dimensional model;

[0061] a repair execution module, configured to calculate a repair level of each component according to the real-time health degree and the remaining life of each component and perform repair on each component according to the repair levels of all components.

[0062] Specifically, in the data online acquisition module, the target mine locomotive refers to a locomotive used in underground or open-pit mine environments such as mines, mine shafts and mining areas to complete transportation tasks, which is taken as a research target of online health monitoring and repair execution in the embodiment. The components of the target mine locomotive include a driving component (engine), a transmission component, a brake component (brake disc), a power supply component (battery) and a hydraulic component (hydraulic pump) and the like. The original state data includes types such as temperature, pressure, speed, friction, voltage and the like; when the original state data is preprocessed, the z-score method is used for standardization to convert the original state data into a fixed range (such as between 0 and 1), and the standard state data is obtained after standardization.

[0063] In the model construction module, the basic three-dimensional model of the target mine locomotive is a three-dimensional digital representation model constructed according to the geometric structures of each component and the whole of the target mine locomotive. When the multiple standard state data of each component is mapped into the basic three-dimensional model, the multiple standard state data of each component is directly bound to the model of the corresponding component in the basic three-dimensional model and visualized.

[0064] In the information generation module, the attribute information of the target mine locomotive includes the standard life of each component, the preset stress amplitude and material constant of each component, the unique identifier of the target mine locomotive and the structure and connection relationship of the target mine locomotive and the like. The state information of the target three-dimensional model includes the multiple standard state data of each component and the attribute information of the target mine locomotive.

[0065] In the real-time health monitoring module, the real-time health degree of a component is a measure for indicating the working state and health condition of the component at the current time. After configuring the real-time health degree for each component in the target three-dimensional model, the value of the real-time health degree of each component is displayed in different colors in the target three-dimensional model, for example, red represents that the value of the real-time health degree of the corresponding component is less than 30, and green represents that the value of the real-time health degree of the corresponding component is greater than 80.

[0066] In the life prediction module, the residual life refers to the time that each component of the target mining locomotive is expected to continue to be used normally without failure or damage. After configuring the residual life for a component in the target three-dimensional model, the residual life of the component is visualized and displayed in the target three-dimensional model.

[0067] In the repair execution module, the repair level refers to a quantitative value for evaluating the repair urgency of the damage and wear of the components of the target mining locomotive during use, which is generally divided into three repair levels: low, medium and high.

[0068] In a specific embodiment, the data online acquisition module comprises:

[0069] The data acquisition unit is configured to acquire a plurality of types of original state data of each component through a plurality of types of sensors pre-configured for each component of the target mining locomotive.

[0070] The wireless transmission unit is configured to acquire the plurality of types of original state data of each component through a wireless transmission mode, and time-align each type of original state data of all components to obtain a plurality of types of standard state data of each component.

[0071] Specifically, in the data acquisition unit, the types of sensors include temperature sensors, pressure sensors, speed sensors, current sensors and the like; and the types of original state data include temperature, pressure, speed, current and the like.

[0072] In the wireless transmission unit, the wireless transmission mode includes WIFI, Bluetooth, cellular network and the like. When time-aligning each type of original state data of all components, first, the plurality of types of original state data of all components are standardized, and then the time of all standardized original state data is aligned according to a pre-set time reference. It should be noted that for the standardized original state data with a sampling frequency lower than the time reference, linear interpolation processing is performed to obtain the standard state data of the standardized original state data.

[0073] In a specific embodiment, the model construction module comprises:

[0074] The base three-dimensional model construction unit is configured to obtain base information of each component of the target mine truck, construct a component three-dimensional model of each component according to the base information of each component, connect the component three-dimensional models of each component based on the structure of the target mine truck, and obtain a base three-dimensional model of the target mine truck.

[0075] The mapping unit is configured to map the multiple standard state data of each component into the component three-dimensional model of each component.

[0076] The integration unit is configured to integrate the component three-dimensional model of each component and the multiple standard state data of each component into the base three-dimensional model, and obtain a target three-dimensional model of the target mine truck.

[0077] Specifically, in the base three-dimensional model construction unit, the base information includes geometric dimensions, shape features, structure features, assembly methods, and connection methods. When obtaining the base information of each component, the base information is obtained based on the composition structure of the target mine truck and the factory information of each component. When generating the component three-dimensional model of each component, the base information of each component is input into a three-dimensional model construction tool for constructing a three-dimensional model, and the three-dimensional model construction tool outputs the component three-dimensional model of each component. The three-dimensional model construction tool includes SolidWorks, AutoCAD, PTC Creo, and Catia, etc. When connecting the component three-dimensional models of each component, an assembly tool is used to butt joint the multiple component three-dimensional models according to the actual connection method. For example, in SolidWorks, the “Mate” function can be used to align different components according to the constraint conditions such as hole position, surface, and edge, and the base three-dimensional model of the target mine truck is obtained.

[0078] In the mapping unit, when the multiple standard state data of each component is mapped into the component three-dimensional model of each component, the corresponding relationship between the standard state data of each component and the component three-dimensional model thereof is established, which facilitates subsequent integration.

[0079] In the integration unit, integration refers to loading the component three-dimensional model of each component and the standard state data thereof into the base three-dimensional model of the target mine truck at the same time, and forming a complete and integrated target three-dimensional model.

[0080] In one specific embodiment, the real-time health monitoring module includes:

[0081] The real-time data acquisition unit is configured to obtain each kind of standard state data of each component at the current time according to the state information as each kind of real-time state data of each component.

[0082] The real-time health degree calculation unit is configured to calculate an entropy health value of the target component according to each real-time state data of the target component, and calculate a real-time health degree of the target component at the current time according to the entropy health value, wherein the target component is any component in the target three-dimensional model.

[0083] The configuration unit is configured to configure a real-time health degree for each component in the target three-dimensional model.

[0084] Specifically, in the real-time data acquisition unit, the real-time state data is standard state data of the component at the current time. The standard state data includes both real-time state data and historical state data.

[0085] In the real-time health degree calculation unit, the entropy health value is an index for evaluating the health degree of each component based on the entropy theory. The higher the entropy health value of a component is, the more chaotic and the worse the health degree of the component is, and vice versa. The real-time health degree is opposite to the change trend of the entropy health value. The larger the real-time health degree is, the better the health degree of the component is.

[0086] After the configuration unit configures a real-time health degree for each component in the target three-dimensional model, the real-time health degree can be displayed in the target three-dimensional model in real time, thereby realizing real-time and intuitive display of the real-time health degree of each component.

[0087] In one specific embodiment, the real-time health degree calculation unit includes:

[0088] The matrix construction sub-unit is configured to construct a real-time matrix according to each real-time state data of the target component, and construct a comparison vector according to a preset standard value corresponding to each real-time state data;

[0089] The distance calculation sub-unit is configured to input the real-time matrix and the comparison vector into a phase space, and calculate Mahalanobis distance between each real-time state data in the real-time matrix and the comparison vector;

[0090] The entropy health value calculation sub-unit is configured to calculate q-entropy of each real-time state data according to the Mahalanobis distance between each real-time state data and the comparison vector, and normalize the q-entropy of all real-time state data to obtain a state entropy health value of each real-time state data;

[0091] The health degree calculation sub-unit is configured to superimpose the state entropy health values of all real-time state data of the target component to obtain an entropy health value of the target component at the current time, multiply a preset health conversion coefficient by the entropy health value of the target component at the current time to obtain a real-time health degree of the target component.

[0092] Specifically, in the matrix constructing subunit, each row of the real-time matrix represents a component, and each column represents a kind of real-time state data; each element of the comparison vector represents a preset standard value of the kind of real-time state data corresponding to the order of each column of real-time state data in the real-time matrix. Wherein, each preset standard value is determined according to experience.

[0093] In the distance calculating subunit, the phase space is a multi-dimensional space, each dimension of which represents a kind of real-time state data. By mapping the various kinds of real-time state data of the target component and the preset standard values into the phase space, different aspects of the various kinds of real-time state data of the dimensions can be highlighted. Mahalanobis distance is a distance measurement method for measuring the similarity between data points. When calculating the Mahalanobis distance D between a kind of real-time state data x and the comparison vector u, formula (2) can be used: In formula (2), T represents transposition, C-1 represents the inverse matrix of the covariance matrix composed of the standard state data corresponding to the position of each kind of real-time state data, and (x-u) represents the matrix composed of the kind of real-time state data and the comparison vector.

[0094] In the entropy health value calculating subunit, when calculating the q-entropy H of a kind of real-time state data according to the Mahalanobis distance D between the kind of real-time state data and the comparison vector, formula (3) can be used:

[0095]

[0096] In formula (3), q represents an adjustment coefficient, ln( ) represents a logarithmic function, D q represents the qth power of the Mahalanobis distance.

[0097] In the health degree calculating subunit, the preset health conversion coefficient is a conversion coefficient determined according to historical experience values.

[0098] In one specific embodiment, the life prediction module comprises:

[0099] a data acquisition unit configured to acquire, according to state information, standard life of each component and multiple standard state data from a starting time of use to a current time, and use the multiple standard state data from the starting time of use to the current time as multiple historical state data;

[0100] a life prediction unit configured to construct a space-time matrix of each component according to the standard life of each component and the multiple historical state data thereof, and predict a remaining life of each component based on the space-time matrix;

[0101] a life configuration unit configured to configure the remaining life for each component in the target three-dimensional model.

[0102] ​​Specifically, the multiple standard state data from the starting time of use of the component to the current time in the data acquisition unit are data obtained during operation of the component, and do not include non-operation data.

[0103] In the life prediction unit, the space-time matrix is a structured data expression method for integrating the standard life of each component and the historical state data and the time dimension. In the space-time matrix of a certain component, each row represents multiple historical state data of a time node, and each column represents the same historical state data under the corresponding time node, and the standard life of the component is placed at the end of each row. For example, the space-time matrix of a certain component can be represented as:

[0104] .

[0105] When the life configuration unit configures the residual life of each component in the target three-dimensional model, it constructs the mapping relationship between the residual life of each component and the corresponding component three-dimensional model, and binds the residual life of each component to the corresponding component three-dimensional model according to the mapping relationship. For example, the residual life of a certain component is displayed next to its component three-dimensional model and is displayed as: residual life 30 days.

[0106] In one specific embodiment, the life prediction unit includes the following when predicting the residual life of each component based on the space-time matrix:

[0107] Calculate the eigenvector of the space-time matrix of each component;

[0108] Construct the fatigue strength curve of each component according to the eigenvector, wherein the horizontal coordinate of the fatigue strength curve is the fatigue time and the vertical coordinate is the fatigue strength;

[0109] According to the fatigue strength curve, obtain the fatigue strength of each component in each future time period, and calculate the residual life of each component according to the preset stress amplitude, material constant and fatigue strength of each component in each future time period.

[0110] Specifically, the eigenvector of the space-time matrix is calculated by statistical analysis of each column in the space-time matrix to obtain the statistical characteristics of the historical state data of each time node. The statistical characteristics of the historical state data of each time node are spliced according to the order of the historical state data categories in the space-time matrix to obtain the eigenvector of the space-time matrix.

[0111] In the calculation of the residual life of a component, a fatigue strength function of a known time period is first constructed according to a preset stress amplitude of the component and a disclosed fatigue strength formula, then the fatigue strength function of the known time period is fitted according to the features of the historical state data of each time node in the feature vector of the component, to obtain a fatigue strength curve, wherein the division of the time period of the horizontal coordinate in the fatigue strength curve is determined according to the fatigue condition of the component in the historical operation process. Then the residual life of the component is calculated according to the preset stress amplitude, material constant and fatigue strength of each future time period of the component.

[0112] The fatigue strength function of a component can be represented by formula (5):

[0113] (5);

[0114] 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 working cycle number of the component, and RD represents the working cycle coefficient. In the fitting, the historical state data of each time node and its features and the working cycle coefficient in the feature vector are fitted to obtain the fatigue strength curve.

[0115] In addition, the preset stress amplitude of a component is a stress level value pre-set by the component; and the material constant of a component is a specific numerical parameter pre-determined according to the empirical value for describing the performance of the material of the component in terms of fatigue, strength, toughness, hardness, etc.

[0116] In a specific embodiment, the repair execution module comprises:

[0117] A repair influence coefficient calculation unit is configured to calculate the repair influence coefficient of each component according to the real-time state data of each component;

[0118] A repair level calculation unit is configured to calculate the repair level of each component according to the real-time health degree, residual life and repair influence coefficient of each component;

[0119] A strategy generation unit is configured to take the components with a repair level greater than a repair threshold as repairable components, and to repair each repairable component according to the size of the repair level of each repairable component.

[0120] Specifically, in the repair influence coefficient calculation unit, the repair influence coefficient is a parameter for measuring the relationship between the state of the component and the repair demand, and is used to evaluate the influence of the real-time state data of the component on the repair level.

[0121] In the repair level calculation unit, when calculating the repair level of each component, the calculation method is: real-time health degree x repair influence coefficient + (1-repair influence coefficient) x residual life.

[0122] a policy generation unit, wherein the repair threshold is a minimum threshold value determined according to an empirical value whether repair is needed.

[0123] In one specific embodiment, the repair influence coefficient calculation unit comprises:

[0124] a state vector construction subunit configured to construct a state vector according to multiple real-time state data of each component;

[0125] a distance calculation subunit configured to calculate an average vector distance of each real-time state data of each component and the state vector;

[0126] a repair influence coefficient subunit configured to probabilize the average vector distance of each component to obtain a repair influence coefficient of each component.

[0127] Specifically, in the state vector construction subunit, the 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, and the state vector constructed according to the three real-time state data is [38, 500, 200].

[0128] In the distance calculation subunit, the average vector distance of a certain component is calculated by taking the average of the vector distances between all real-time state data of the component and the state vector, wherein the vector distance between each real-time state data of each component and the state vector is calculated by a cosine similarity formula.

[0129] In the repair influence coefficient subunit, the probabilization of the average vector distance of each component is performed by an exponential function, as shown in formula (4):

[0130] (4);

[0131] In formula (4), R represents the repair influence coefficient of a certain component, avg(d) represents the average vector distance of the component, exp() represents an exponential function, and b represents an 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.

[0132] In one specific embodiment, when calculating the residual life N of any component according to the preset stress amplitude, material constant and fatigue strength of each future time period of the component, formula (1) is used:

[0133] (1);

[0134] In formula (1), Ci represents the fatigue strength of the i-th future time period, S represents a preset stress amplitude of the component, and m represents a material constant of the component.

[0135] Specifically, the formula (1) describes the residual life of the component by linearizing material damage accumulation of the component.

[0136] According to all the above embodiments, the online health monitoring and repair execution system for the mine locomotive provided by the embodiments has the following beneficial effects:

[0137] Firstly, the data online acquisition module online acquires and pre-processes various original state data of each component of the target mine locomotive, obtains various standard state data of each component, and provides accurate and diverse data basis for subsequent health state evaluation and life evaluation of the target mine locomotive.

[0138] Then, the model construction module maps the various standard state data of each component to the basic three-dimensional model to obtain the target three-dimensional model of the target mine locomotive, which can visually display the real-time state of each component of the target mine locomotive through the target three-dimensional model, facilitate intuitive obtaining of the real-time state of the target mine locomotive, and improve the convenience of visualizing the health degree evaluation result of each component.

[0139] Then, the real-time health monitoring module calculates the real-time health degree of each component according to the state information, and configures the real-time health degree of each component in the target three-dimensional model, and the life prediction module predicts the residual life of each component according to the state information, and configures the residual life of each component in the target three-dimensional model, to realize real-time determination of the health degree and residual life of each component of the target mine locomotive, facilitate quick and accurate determination of the occurrence position of real-time abnormalities and potential risks of the target mine locomotive, and improve the accuracy and effectiveness of repair; by configuring the real-time health degree and residual life of each component in the target three-dimensional model, the visual display of the real-time health degree and residual life is realized, the monitoring and management of each component through the target three-dimensional model become more intuitive and operable, and the management efficiency and decision-making speed are greatly improved.

[0140] Finally, the repair execution module calculates the repair level of each component in combination with the real-time health degree and residual life of each component, and repairs each component, to realize predictive repair based on the real-time health degree and residual life of each component, effectively improve the accuracy and timeliness of the repair strategy, and optimize resource allocation.

[0141] The above merely describes the preferred embodiments of the present application and is not intended to limit the present application. It should be pointed out that, for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present application, and these improvements and modifications should also be considered as falling within the protection scope of the present application.

Claims

1. A mining locomotive online health monitoring and repair execution system, characterized in that, The method comprises the following steps: a data online acquisition module is used for acquiring various original state data of each component of the target mine locomotive in real time, and pre-processing the original state data to obtain various standard state data of each component; a model construction module is used for constructing a basic three-dimensional model of the target mine locomotive, and mapping the various standard state data of each component into the basic three-dimensional model to obtain a target three-dimensional model of the target mine locomotive; an information generation module is used for generating state information of the target three-dimensional model according to the various standard state data of each component and attribute information of the target mine locomotive; a real-time health monitoring module is used for calculating a real-time health degree of each component at the current time according to the state information, and configuring the real-time health degree for each component in the target three-dimensional model; the real-time health monitoring module comprises: a real-time data acquisition unit is used for acquiring each standard state data of each component at the current time as each real-time state data of each component according to the state information; a real-time health degree calculation unit is used for calculating an entropy health value of a target component through each real-time state data of the target component, and calculating a real-time health degree of the target component at the current time according to the entropy health value, wherein the target component is any component in the target three-dimensional model; a configuration unit is used for configuring the real-time health degree for each component in the target three-dimensional model; the real-time health degree calculation unit comprises: a matrix construction sub-unit is used for constructing a real-time matrix according to each real-time state data of the target component, and constructing a comparison vector according to a preset standard value corresponding to each real-time state data; a distance calculation sub-unit is used for inputting the real-time matrix and the comparison vector into a phase space, and calculating a Mahalanobis distance between each real-time state data in the real-time matrix and the comparison vector; an entropy health value calculation sub-unit is used for calculating a q-entropy of each real-time state data according to the Mahalanobis distance between each real-time state data and the comparison vector, and performing normalization processing on the q-entropies of all real-time state data to obtain a state entropy health value of each real-time state data; a health degree calculation sub-unit is used for superimposing the state entropy health values of all real-time state data of the target component to obtain an entropy health value of the target component at the current time, multiplying a preset health conversion coefficient with the entropy health value of the target component at the current time to obtain a real-time health degree of the target component; a life prediction module is used for predicting a remaining life of each component according to the state information, and configuring the remaining life for each component in the target three-dimensional model; the life prediction module comprises: a data acquisition unit is used for acquiring a standard life of each component and various standard state data from a starting use time to the current time according to the state information, and taking the various standard state data from the starting use time to the current time as various historical state data; a life prediction unit is used for constructing a space-time matrix of each component according to the standard life of each component and the various historical state data thereof, and predicting a remaining life of each component based on the space-time matrix; a life configuration unit is used for configuring the remaining life for each component in the target three-dimensional model. The repair execution module is configured to calculate a repair level of each component according to the real-time health degree and the residual life of each component, and to repair each component according to the repair levels of all the components.

2. The online health monitoring and repair execution system for mine locomotive according to claim 1, characterized in that, The data online acquisition module comprises: The data acquisition unit is configured to acquire a plurality of original state data of each component through a plurality of types of sensors pre-configured for each component of the target mine locomotive; The wireless transmission unit is configured to acquire the plurality of original state data of each component through a wireless transmission mode, and to time-align each original state data of all the components to obtain a plurality of standard state data of each component.

3. The online health monitoring and repair execution system for mine locomotive according to claim 1, characterized in that, The model construction module comprises: The basic three-dimensional model construction unit is configured to acquire basic information of each component of the target mine locomotive, to construct a component three-dimensional model of each component according to the basic information of each component, and to connect the component three-dimensional models of each component based on the structure of the target mine locomotive to obtain a basic three-dimensional model of the target mine locomotive; The mapping unit is configured to map the plurality of standard state data of each component into the component three-dimensional model of each component; The integration unit is configured to integrate the component three-dimensional model of each component and the plurality of standard state data of each component into the basic three-dimensional model to obtain a target three-dimensional model of the target mine locomotive.

4. The online health monitoring and repair execution system for mine locomotive according to claim 1, characterized in that, When predicting the residual life of each component based on the space-time matrix, the life prediction unit comprises: calculating a feature vector of the space-time matrix of each component; constructing a fatigue strength curve of each component according to the feature vector, wherein the abscissa of the fatigue strength curve is fatigue time and the ordinate is fatigue strength; obtaining the fatigue strength of each component in each future time period according to the fatigue strength curve, and calculating the residual life of each component according to the preset stress amplitude, material constant and fatigue strength of each component in each future time period.

5. The online health monitoring and repair execution system for mine locomotive according to claim 1, characterized in that, The repair execution module comprises: The repair influence coefficient calculation unit is configured to calculate a repair influence coefficient of each component according to the plurality of real-time state data of each component; The repair level calculation unit is configured to calculate a repair level of each component according to the real-time health degree, the residual life and the repair influence coefficient of each component; The strategy generation unit is configured to sort and repair each to-be-repaired component according to the size of the repair level of each to-be-repaired component.

6. The online health monitoring and repair execution system for mine locomotive according to claim 5, characterized in that, The repair influence coefficient calculation unit comprises: The state vector construction subunit is configured to construct a state vector according to the plurality of real-time state data of each component; The distance calculation subunit is configured to calculate an average vector distance between each real-time state data of each component and the state vector; The repair influence coefficient subunit is configured to probabilize the average vector distance of each component to obtain a repair influence coefficient of each component.

7. The online health monitoring and repair execution system for mine locomotive according to claim 4, characterized in that, When calculating the residual life N of any component according to the preset stress amplitude, material constant and fatigue strength of each future time period of the component, it is realized through formula (1): （1）； In Equation (1), Ci represents the fatigue strength of a future i-th time period, represents the sum of the fatigue strengths of all future time periods, S represents a preset stress amplitude value of the component, and m represents a material constant of the component.

Images