Battery status evaluation method, system and unmanned mining truck in open-air environment
By deploying a convolutional neural network evaluation model on an unmanned mine card, combining temperature, humidity and dust data, the accuracy and real-time problems of battery status evaluation in open-air environments are solved, and accurate information on battery capacity degradation is provided, supporting Efficient battery maintenance and vehicle scheduling.
Patent Information
- Application Number
- CN202411154281.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-22
- Publication Date
- 2024-12-20
- Estimated Expiration
- 2044-08-22
AI Technical Summary
The prior art cannot accurately and in real time evaluate the state of unmanned mine cards in open-air environments, especially the fluctuations of temperature, humidity and dust are not fully considered, resulting in inaccurate evaluation of battery status and cannot be applied to vehicle scheduling.
The evaluation model is established using a convolutional neural network, deployed on edge devices, collects temperature, humidity and dust data through sensors, inputs the model to evaluate the battery status, and determines the capacity degradation based on the evaluation results, providing an accurate and real-time battery status reflection.
It realizes accurate and timely evaluation of the battery status in an open-air environment, provides an accurate basis for battery capacity attenuation, and supports effective battery maintenance and vehicle scheduling.
Smart Images
Figure CN118671606B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of battery evaluation technology, and in particular to a method and system for evaluating the battery status of an unmanned mining truck in an open-air environment, and an unmanned mining truck. Background Art
[0002] Unmanned mining trucks, the full name of which is unmanned mining trucks, are new mining equipment that mainly use batteries as energy sources. Unmanned mining trucks complete various tasks in an orderly manner under the control of the dispatching center, which can improve the modernization level of mine production while also improving the efficiency of the mine.
[0003] Unlike indoor and other outdoor environments, open-pit mines have large fluctuations in environmental factors such as temperature, humidity and dust, especially for unmanned mining trucks that work 24 hours a day. The changes in these factors will cause fluctuations in the battery status, so accurate and real-time evaluation of the battery status is required to provide an important basis for vehicle scheduling.
[0004] However, the current assessment method does not take into account the actual influencing factors of open-pit mines, such as temperature, humidity and dust, resulting in inaccurate assessment results of battery status. The current assessment method is mainly periodic testing, which cannot reflect the real-time status of the battery and cannot be applied to vehicle scheduling. Summary of the invention
[0005] The embodiments of the present application provide a method, system and unmanned mining truck for evaluating the battery status in an open-air environment, so as to solve the problems in the prior art of inaccurate battery status evaluation results and poor real-time performance.
[0006] On the one hand, the embodiment of the present application provides a method for evaluating the battery status of an unmanned mining truck in an open-air environment, including:
[0007] An evaluation model is established. The evaluation model uses a convolutional neural network. The evaluation model is converted into a format suitable for edge devices on unmanned mining trucks and deployed on edge devices.
[0008] Collect environmental impact data, including temperature, humidity and dust concentration;
[0009] Input the environmental impact data into the assessment model to obtain the battery status assessment result;
[0010] The capacity degradation of the battery is determined based on the battery status assessment result.
[0011] On the other hand, the embodiment of the present application also provides an unmanned mining truck battery status assessment system in an open-air environment, including:
[0012] A sensor unit, used to collect environmental impact data, including temperature, humidity and dust concentration;
[0013] The edge device is installed on the unmanned mining truck. An evaluation model is deployed in the edge device. The evaluation model adopts a convolutional neural network. The evaluation model is converted into a format suitable for the edge device and deployed on the edge device. The edge device is used to input the environmental impact data into the evaluation model to obtain the battery status evaluation result. Then, the battery capacity degradation is determined based on the battery status evaluation result.
[0014] On the other hand, an embodiment of the present application also provides an unmanned mining truck, including a vehicle and the above-mentioned sensor unit and edge device.
[0015] The method, system and unmanned mining truck battery status assessment system in an open-air environment of the present application have the following advantages:
[0016] At the same time, environmental factors including temperature, humidity and dust are taken into consideration, and a neural network model is used to evaluate the battery status, which can accurately and real-time reflect the true status of the battery. It also calculates the battery capacity attenuation based on the battery status, providing an accurate basis for battery maintenance. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0018] Figure 1 A flow chart of a method for evaluating the battery status of an unmanned mining truck in an open-air environment provided in an embodiment of the present application. DETAILED DESCRIPTION
[0019] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0020] Figure 1 Flow chart of a method for evaluating the battery status of an unmanned mining truck in an open-air environment provided by an embodiment of the present application. The present application embodiment provides a method for evaluating the battery status of an unmanned mining truck in an open-air environment, comprising:
[0021] S100, establishes an evaluation model. The evaluation model uses a convolutional neural network. The evaluation model is converted into a format suitable for edge devices on unmanned mining trucks and is deployed on edge devices.
[0022] Exemplarily, a convolutional neural network is a commonly used neural network. The multi-layer structure in the convolutional neural network can be divided into an input layer, a hidden layer, and an output layer according to the position, and can be divided into a convolutional layer and a pooling layer according to the function. In an embodiment of the present application, the convolutional neural network used in the evaluation model includes three convolutional layers and two pooling layers connected in sequence, wherein each convolutional layer is connected to a ReLU (linear rectification function) activation function, and the last pooling layer uses a softmax function for classification. The convolutional layer is used to extract the features of the input data, while the pooling layer is used to connect the outputs of multiple nodes in the convolutional layer and perform multi-classification processing. The classification results can be simply divided into excellent, good, general, and poor.
[0023] After the evaluation model is established, it is necessary to train the evaluation model. Before training, the sample set is divided into training set, validation set and test set in a ratio of 7:1.5:1.5, and then the evaluation model is trained using the training set and the train_test_split method in Scikit-learn. During the training process, the batch size is set to 32 and the number of iterations is set to 100. After each iteration, the ModelCheckpoint and EarlyStopping in Keras are used to verify the loss size of the iteration result, and then the subsequent iteration processing is adjusted to prevent overfitting.
[0024] Furthermore, TensorFlow Lite can be used to convert the evaluation model into a format suitable for edge devices.
[0025] S110, collecting environmental impact data, the environmental impact data including temperature, humidity and dust concentration.
[0026] Exemplarily, a sensor unit is provided on the unmanned mining truck, and the sensor unit includes a temperature sensor, a humidity sensor and a dust concentration sensor as required, which are used to collect temperature, humidity and dust concentration respectively.
[0027] S120, inputting the environmental impact data into the evaluation model to obtain a battery status evaluation result.
[0028] Exemplarily, the edge device can be installed on an unmanned mining truck. After the sensor unit collects temperature, humidity and dust concentration, the sensor unit transmits the environmental impact data to the edge device through a data cable. The edge device inputs the environmental impact data into the evaluation model to obtain the battery status evaluation result.
[0029] The battery state can be described by mathematical model:
[0030]
[0031] in, X ( t ) is the battery status assessment result, A ( t ) is the battery itself in time t Chemical aging data, T ( t ) is the temperature, H ( t ) is humidity, D ( t ) is the dust concentration, f In order to represent the nonlinear function of the battery state affected by the environment, it is implemented by the evaluation model in the actual processing process.
[0032] Mathematically, the environmental impact function f It can be described as:
[0033]
[0034] in, w A , w T , w H and w D is the weight coefficient of each item, It is a mapping function of the effects of temperature, humidity, and dust concentration on the battery, and is usually a nonlinear function such as a sigmoid function.
[0035] Before inputting the environmental impact data into the assessment model, the environmental impact data is also filtered using a bandpass filter.
[0036] When collecting environmental impact data, you can collect environmental impact data within a time window of a set length, such as 30 minutes, and then input the data into the assessment model after the collection is completed.
[0037] Furthermore, after collecting the environmental impact data and filtering it, Python's Pandas library is used to calculate the statistical characteristics of the environmental impact data within the time window, including the mean, maximum, minimum and standard deviation. Python's Numpy library is then used to perform a fast Fourier transform on the statistical features to extract the frequency domain features of the statistical features, which are then input into the evaluation model.
[0038] S130, determining the capacity degradation of the battery according to the battery status evaluation result.
[0039] For example, based on the above battery status evaluation results X ( t ), the capacity degradation can be expressed as:
[0040]
[0041] in, C ( t ) is the current remaining capacity, C 0 is the initial capacity, e is a natural constant, t 1 for t The upper limit of the value of X ( t ) is the battery status assessment result, t Indicates time, dt Indicates time t The differential of k ( X ( t )) is the degradation rate function, expressed as:
[0042]
[0043] in, k 0 and k 1 are all constants, representing the basic degradation rate and health status bonus degradation rate respectively.
[0044] The embodiment of the present application also provides a battery status assessment system for unmanned mining trucks in an open-air environment, the system comprising:
[0045] A sensor unit, used to collect environmental impact data, including temperature, humidity and dust concentration;
[0046] The edge device is installed on the unmanned mining truck. An evaluation model is deployed in the edge device. The evaluation model adopts a convolutional neural network. The evaluation model is converted into a format suitable for the edge device and deployed on the edge device. The edge device is used to input the environmental impact data into the evaluation model to obtain the battery status evaluation result. Then, the battery capacity degradation is determined based on the battery status evaluation result.
[0047] Exemplarily, the edge device is an NVIDIA Jetson device or a Google Coral device.
[0048] An embodiment of the present application also provides an unmanned mining truck, including a vehicle and the above-mentioned sensor unit and edge device.
[0049] Exemplarily, the edge device is connected to the dispatching center via a wireless communication network. After the sensor unit collects environmental impact data, the edge device can process it in real time. The obtained battery status assessment results and capacity degradation conditions are transmitted to the dispatching center via the wireless communication network. Based on this information, the dispatching center can plan the best task allocation plan to efficiently and accurately complete various tasks in the mine.
[0050] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.
[0051] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.
Claims
1. Battery status assessment method for unmanned mining trucks in open-air environments, It is characterized in that include: Establishing an evaluation model, wherein the evaluation model adopts a convolutional neural network, the evaluation model is converted into a format suitable for edge devices on unmanned mining trucks, and is deployed on the edge devices; Collecting environmental impact data, including temperature, humidity and dust concentration; Inputting the environmental impact data into the evaluation model to obtain a battery status evaluation result; Determining the capacity degradation of the battery according to the battery status evaluation result; The evaluation model comprises three convolutional layers and two pooling layers connected in sequence, wherein each convolutional layer is connected to a ReLU activation function, and the last pooling layer adopts a softmax function for classification; The battery status evaluation result is described by a mathematical model: in, X ( t ) is the battery status evaluation result, A ( t ) is the battery itself in time t Chemical aging data, T ( t ) is the temperature, H ( t ) is humidity, D ( t ) is the dust concentration, f is a nonlinear function that represents the impact of the battery state on the environment; Mathematically, the environmental impact function f Described as: in, w A , w T , w H and w D is the weight coefficient of each item, It is a mapping function of the effects of temperature, humidity, and dust concentration on the battery; The capacity degradation is expressed as: in, C ( t ) is the current remaining capacity, C 0 is the initial capacity, e is a natural constant, t 1 for t The upper limit of the value of X ( t ) is the battery status evaluation result, t Indicates time, dt Indicates time t The differential of k ( X ( t )) is the degradation rate function, expressed as: in, k 0 and k 1 are all constants.
2. According to the method for evaluating the battery status of unmanned mining trucks in an open-air environment in claim 1, It is characterized in that Before the environmental impact data is input into the evaluation model, the environmental impact data is filtered using a bandpass filter.
3. According to the method for evaluating the battery status of unmanned mining trucks in an open-air environment in claim 1, It is characterized in that When collecting the environmental impact data, the environmental impact data is collected within a time window of a set length, and is input into the assessment model after the collection is completed.
4. According to the method for evaluating the battery status of unmanned mining trucks in an open-air environment in claim 3, It is characterized in that After the environmental impact data is collected, the statistical features of the environmental impact data within the time window are calculated, and then the statistical features are subjected to fast Fourier transform to extract the frequency domain features of the statistical features, and then the frequency domain features are input into the evaluation model.
5. According to the method for evaluating the battery status of unmanned mining trucks in an open-air environment in claim 1, It is characterized in that TensorFlow Lite is used to convert the evaluation model into a format suitable for the edge device.
6. A battery status assessment system for unmanned mining trucks in an open-air environment, the system applying the battery status assessment method for unmanned mining trucks in an open-air environment according to any one of claims 1 to 5, It is characterized in that The system comprises: A sensor unit, used to collect environmental impact data, wherein the environmental impact data includes temperature, humidity and dust concentration; An edge device is installed on an unmanned mining truck. An evaluation model is deployed in the edge device. The evaluation model adopts a convolutional neural network. The evaluation model is converted into a format suitable for the edge device and deployed on the edge device. The edge device is used to input the environmental impact data into the evaluation model to obtain a battery status evaluation result; and then determine the capacity degradation of the battery according to the battery status evaluation result.
7. The unmanned mining truck battery status assessment system in an open-air environment according to claim 6, It is characterized in that The edge device adopts an NVIDIA Jetson device or a Google Coral device.
8. The unmanned mining truck battery status assessment system in an open-air environment according to claim 6, It is characterized in that It also includes a vehicle, and the sensor unit, the edge device and the vehicle constitute an unmanned mining truck.