Intelligent power management method and intelligent power management device

Abstract

The embodiments of the present disclosure provide an intelligent power management method and an intelligent power management device, which are applied to the field of intelligent control technology. The method includes: based on multiple bus multiplexing, obtaining real-time data of multiple devices; analyzing the real-time data through a fault monitoring and diagnosis model to determine whether there is a fault, and if so, predicting the fault type; matching the corresponding fault solution according to the fault type for easy maintenance; analyzing the real-time data through a fuse life prediction model to predict the life status of the fuse; if the predicted fuse life status is not good, sending a fuse replacement reminder; if it is detected that the fault is cleared or the fuse replacement is completed, the power supply is automatically restored. In this way, the vehicle wiring harness can be reduced, the maintenance efficiency can be improved, and the intelligent level of vehicle power management can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent control technology, and in particular to an intelligent power management method and an intelligent power management device. Background Art

[0002] With the continuous increase of electronic equipment in vehicles, the wiring harness connections in the car are becoming more and more complicated, which not only increases the cost and vehicle weight, but also makes line faults more likely to occur. The traditional on-board power management system lacks intelligent management units for specific load characteristics, real-time status monitoring, and rapid response to abnormal situations. Therefore, fault detection requires manual troubleshooting, and due to the complexity of the wiring harness, troubleshooting is difficult and maintenance efficiency is low. At the same time, the traditional on-board power management system also has problems such as fuse status monitoring and lack of intelligence in the recovery process after fault clearing. Summary of the invention

[0003] In view of this, the present disclosure provides an intelligent power management method and an intelligent power management device.

[0004] According to a first aspect of the present disclosure, there is provided an intelligent power management method, the method comprising:

[0005] Based on multiple bus multiplexing, real-time data of multiple devices are obtained; through the fault monitoring and diagnosis model, the real-time data is analyzed to determine whether there is a fault, and if so, the fault type is predicted; the corresponding fault solution is matched according to the fault type to facilitate maintenance; through the fuse life prediction model, the real-time data is analyzed to predict the life status of the fuse; if the predicted fuse life status is not good, a fuse replacement reminder is sent; if it is detected that the fault is cleared or the fuse replacement is completed, the power supply is automatically restored.

[0006] In some embodiments of the first aspect, based on multiple bus multiplexing, real-time data of multiple devices are obtained, including: based on multiple bus multiplexing, using one or more shared buses to obtain real-time data of multiple devices.

[0007] In some embodiments of the first aspect, real-time data is analyzed by a fault monitoring and diagnosis model to determine whether a fault exists, and if so, the fault type is predicted; and a corresponding fault solution is matched according to the fault type to facilitate maintenance, including:

[0008] Through the fault monitoring and diagnosis model, the real-time data is compared with the preset threshold to determine whether the real-time data exceeds the preset threshold. If it exceeds the preset threshold, it is determined that a fault exists, and the fault type is predicted based on the fault data;

[0009] According to the fault type, the corresponding fault solution is matched in the preset fault solution library to facilitate maintenance.

[0010] In some embodiments of the first aspect, the fault monitoring and diagnosis model is obtained by the following training:

[0011] The data of the equipment and the working condition data of the vehicle at each historical moment are used as the input data of the model, and the fault state and type corresponding to the data of the equipment and the working condition data of the vehicle at each historical moment are used as labels to generate a training set;

[0012] Use the training set to train the model and update the parameters until a fault monitoring and diagnosis model is generated.

[0013] In some embodiments of the first aspect, the fuse life prediction model is obtained by the following training:

[0014] The current load and temperature change data of the fuse at each historical moment and the operating condition data of the vehicle are used as the input data of the model, and the fuse life status corresponding to the current load and temperature change data of the fuse at each historical moment and the operating condition data of the vehicle are used as labels to generate a training set;

[0015] The training set is used to train the model and update the parameters until a fuse life prediction model is generated.

[0016] In some embodiments of the first aspect, if it is detected that the fault is cleared or the fuse is replaced, the power supply is automatically restored, including:

[0017] For a circuit that stops supplying power due to a fault, if the monitored parameters return to the normal range and remain stable, it is confirmed that the fault has been cleared;

[0018] For the circuit that stops power supply due to fuse replacement, check the status of the fuse. If it works normally and the fuse life is good, it is confirmed that the fuse replacement is successful;

[0019] Once the fault is cleared or the fuse is replaced, power will be automatically restored to allow the device to resume normal operation.

[0020] According to a second aspect of the present disclosure, there is provided an intelligent power management device, the intelligent power management device comprising:

[0021] An acquisition unit, used for acquiring real-time data of multiple devices based on multiple bus multiplexing;

[0022] The fault diagnosis and display unit is used to analyze the real-time data through the fault monitoring and diagnosis model to determine whether there is a fault and predict the fault type if there is one; match the corresponding fault solution according to the fault type to facilitate maintenance;

[0023] The fuse monitoring unit is used to analyze the real-time data through the fuse life prediction model to predict the life status of the fuse; if the predicted life status of the fuse is not good, a fuse replacement reminder is sent;

[0024] The self-recovery unit is used to automatically restore power supply if it detects that the fault has been cleared or the fuse has been replaced.

[0025] According to a third aspect of the present disclosure, an electronic device is provided. The electronic device includes: at least one processor; and a memory connected to the at least one processor in communication; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described above.

[0026] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to cause a computer to execute the method described above.

[0027] According to a fifth aspect of the present disclosure, a vehicle is provided, to which the above-described method is applied.

[0028] In the present disclosure, real-time data of multiple devices are obtained through multiplexing of multiple buses, which reduces the use of wiring harnesses, reduces costs and vehicle weight; the fault monitoring and diagnosis model is used to quickly and accurately determine the fault type and provide corresponding solutions, thereby improving maintenance efficiency; the fuse life status can be warned in advance through the fuse life prediction model, and a replacement reminder can be sent to avoid circuit problems caused by fuse failure, thereby improving vehicle safety; and the power supply is automatically restored after the fault is cleared or the fuse is replaced, thereby improving the intelligence level of vehicle power management.

[0029] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, among which:

[0031] Figure 1 A flow chart of an intelligent power management method provided by an embodiment of the present disclosure is shown;

[0032] Figure 2 A block diagram of an intelligent power management device according to an embodiment of the present disclosure is shown;

[0033] Figure 3 A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0035] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0036] In view of the problems mentioned in the background technology, the present disclosure provides an intelligent power management method and an intelligent power management device.

[0037] Specifically, based on multi-channel bus multiplexing, real-time data of multiple devices are obtained; through the fault monitoring and diagnosis model, the real-time data is analyzed to determine whether there is a fault, and if so, the fault type is predicted; the corresponding fault solution is matched according to the fault type to facilitate maintenance; through the fuse life prediction model, the real-time data is analyzed to predict the life status of the fuse; if the predicted fuse life status is not good, a fuse replacement reminder is sent; if it is detected that the fault is cleared or the fuse replacement is completed, the power supply is automatically restored.

[0038] In this way, the number of vehicle wiring harnesses can be reduced, the fault location and type can be quickly located and corresponding solutions can be provided, the safety of the vehicle can be improved, and the intelligence level of vehicle power management can be improved.

[0039] The present disclosure is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0040] Figure 1 A flow chart of an intelligent power management method provided by an embodiment of the present disclosure is shown; Figure 1 As shown, the intelligent power management method 100 may include:

[0041] S110, based on multiple bus multiplexing, obtains real-time data of multiple devices.

[0042] Specifically, based on multiplexed bus multiplexing, the real-time data of other devices associated with the bus can be simultaneously acquired through one or more shared buses. By utilizing the sharing mechanism of multiple buses, the real-time data of all devices on the shared path can be acquired simultaneously by simply placing the data acquisition device on one or more shared buses, without having to use multiple complex wiring harnesses to acquire the real-time data of each device separately as in the traditional way. For example, to acquire data of multiple components on a vehicle (such as an instrument panel, an air-conditioning compressor), it is only necessary to connect the signal pins of the acquisition device to the bus. Some other devices are also arranged on the bus, and these other devices will also generate corresponding raw data information. At this time, the relevant information of the instrument panel / air-conditioning compressor can be indirectly obtained by reading the data on the bus, which greatly simplifies the hardware architecture and improves the development efficiency. Among them, multiplexed bus multiplexing includes but is not limited to: CAN, I²C, SPI, etc.

[0043] In traditional vehicle-mounted device communications, each device may require a separate line to transmit status information and control instructions, which results in a large number of wiring harnesses. Bus multiplexing technology allows one bus to transmit status information and control instructions for multiple devices. Taking multiple sensors and actuators in a vehicle as an example, in traditional methods, each sensor (for example, temperature sensor, pressure sensor, etc.) and actuator (for example, motor, valve, etc.) may require a separate signal line to connect to the controller. After adopting bus multiplexing technology, multiple sensors and actuators can share one bus and transmit data on the bus through different addresses or identifiers.

[0044] For example, multiple sensors in the engine control system (eg, water temperature sensor, intake pressure sensor, etc.) can transmit collected data to the engine control unit via the CAN bus. At the same time, the engine control unit can also send control instructions to actuators (eg, fuel injectors, throttles, etc.) via the CAN bus.

[0045] According to the embodiments of the present disclosure, based on multiplexed buses, one or more shared buses are used to obtain real-time data of multiple devices, which greatly reduces the number of wiring harnesses, makes vehicle wiring more concise, and reduces the probability of line failure.

[0046] S120, analyzing the real-time data through the fault monitoring and diagnosis model to determine whether there is a fault, and if so, predicting the fault type; matching the corresponding fault solution according to the fault type to facilitate maintenance.

[0047] Specifically, through the fault monitoring and diagnosis model, the real-time data is compared with the normal data to determine whether the real-time data exceeds the preset threshold. If it exceeds the preset threshold, it is determined that a fault exists, and the fault type is predicted based on the fault data; based on the fault type, the corresponding fault solution is matched in the preset fault solution library to facilitate maintenance.

[0048] More specifically, the real-time input and output voltage, current, temperature and other parameters are obtained through the microcontroller, and the parameters are input into the fault monitoring and diagnosis model for analysis to determine whether the real-time data exceeds the preset threshold. If it exceeds the preset threshold, it is determined that a fault exists, and the fault type is predicted based on the fault data; according to the fault type, the corresponding fault solution is matched in the preset fault solution library; an LCD, LED or OLED display is integrated, and connected to the internal controller of the power management box through a serial port, I²C or SPI interface to send the fault type and solution to the display so that relevant personnel can perform quick repairs.

[0049] Taking an OLED display connected with an SPI interface as an example, when the fault monitoring and diagnosis model detects that the input voltage is lower than the normal range, it predicts that it is a low input voltage fault. The matching solution is: check whether the generator belt is loose, check whether the generator is damaged, check whether the connection line has poor contact, etc.; after the controller receives the data output by the model, it sends the data containing fault information, fault type and solution to the OLED display through the SPI interface, and the display displays the data after receiving the data.

[0050] Furthermore, the fault monitoring and diagnosis model is obtained through the following training:

[0051] The equipment data and vehicle operating data at each historical moment are used as the input data of the model, and the fault status and type corresponding to the equipment data and vehicle operating data at each historical moment are used as labels to generate a training set; the training set is used to train the model and update the parameters until a fault monitoring and diagnosis model is generated. Specifically:

[0052] Device data can include: Input voltage V in , output current I out , Equipment temperature T device .

[0053] Vehicle operating data may include: driving speed v vehicle , acceleration a vehicle 、Road information condition .

[0054] The fault status can be represented by binary code, for example, "0" represents normal status and "1" represents fault status; the fault type can be represented by digital code, such as short circuit fault is 10, overload fault is 20, internal equipment fault is 30, etc.

[0055] Assume that data from N historical moments are collected over a period of time. The data from each historical moment includes equipment data and vehicle operating condition data as well as corresponding fault status and type labels. These data are organized into a training set X in the form of a matrix and a corresponding label vector Y.

[0056] X = [x1, x2, ..., x N ], where x i = [V in_i , I out_i , T device_i , v vehicle_i , a vehicle_i ,road condition_i ].

[0057] Y = [y1, y2, ..., y N ], where y i are the corresponding fault status and type labels.

[0058] The multi-layer perceptron MLP in the machine learning algorithm can be selected to train the model. The input layer of the MLP receives the above input data, the hidden layer performs nonlinear transformation on the data through the activation function, and the output layer outputs the predicted fault status and type.

[0059] Define a loss function to measure the difference between the model prediction and the true label. The loss function can use the cross entropy loss function.

[0060] The training set X is input into the model, the output of the model is calculated through forward propagation, the loss value is calculated according to the loss function, the gradient of the loss function to the model parameters is calculated using the back propagation algorithm, and the model parameters are updated using an optimization algorithm (e.g., stochastic gradient descent) to minimize the loss function. The process is repeated until the required fault monitoring and diagnosis model is generated.

[0061] The following is a code example to explain the above content in more detail:

[0062] import numpy as np

[0063] from sklearn.neural_network import MLPClassifier

[0064] import torch

[0065] import torch.nn as nn

[0066] import torch.optim as optim

[0067] # Real-time data

[0068] N = 100

[0069] Vin = np.random.uniform(10, 15, N)

[0070] Iout = np.random.uniform(1, 5, N)

[0071] Tdevice = np.random.uniform(30, 50, N)

[0072] vvehicle = np.random.uniform(50, 100, N)

[0073] avehicle = np.random.uniform(1, 3, N)

[0074] roadcondition = np.random.choice([0, 1], N)

[0075] fault_status = np.random.choice([0, 1], N)

[0076] fault_type = np.random.choice([10, 20, 30], N)

[0077] # Training set and labels

[0078] X = np.array([Vin, Iout, Tdevice, vvehicle, avehicle,roadcondition]).T

[0079] Y = np.array([fault_status, fault_type]).T

[0080] # Define a multi-layer perceptron model

[0081] class MLP(nn.Module):

[0082] def __init__(self):

[0083] super(MLP, self).__init__()

[0084] self.fc1 = nn.Linear(6, 10)

[0085] self.relu = nn.ReLU()

[0086] self.fc2 = nn.Linear(10, 2)

[0087] def forward(self, x):

[0088] out = self.fc1(x)

[0089] out = self.relu(out)

[0090] out = self.fc2(out)

[0091] return out

[0092] model = MLP()

[0093] # Define the loss function and optimizer

[0094] criterion = nn.CrossEntropyLoss()

[0095] optimizer = optim.SGD(model.parameters(), lr=0.01)

[0096] # Train the model

[0097] for epoch in range(100):

[0098] optimizer.zero_grad()

[0099] outputs = model(torch.from_numpy(X).float())

[0100] loss = criterion(outputs, torch.from_numpy(Y).long().view(-1))

[0101] loss.backward()

[0102] optimizer.step()

[0103] The above code defines a class named MLP, defines the first fully connected layer, with an input dimension of 6 (corresponding to the number of equipment data and vehicle operating condition data) and an output dimension of 10, defines a ReLU activation function to introduce nonlinearity in the hidden layer, and also defines a second fully connected layer with an input dimension of 10 (from the output of the first fully connected layer) and an output dimension of 2 (corresponding to the combination of fault state and fault type). It further defines the forward propagation process of the model, where the input x passes through the first fully connected layer, the ReLU activation function, and the second fully connected layer, and finally outputs the prediction result; the model selects the cross entropy loss function as the loss function of the model, which is suitable for multi-classification problems, selects stochastic gradient descent (SGD) as the optimization algorithm, and sets the learning rate to 0.01 to update the parameters of the model to minimize the loss function.

[0104] In the training loop, first clear the gradient of the optimizer to avoid accumulating gradients in each iteration, convert the training set data into a PyTorch tensor, and pass it into the model for forward propagation to get the model output; calculate the loss function, take the model output and the true label as input, convert the label into a long integer, and flatten it into a one-dimensional tensor to meet the requirements of the loss function, perform backpropagation, calculate the gradient of the loss function with respect to the model parameters, and update the model parameters according to the calculated gradient.

[0105] Here is an example prediction:

[0106] # Real-time data

[0107] new_data = np.array([[12, 3.5, 40, 80, 2, 0]])

[0108] new_data_tensor = torch.from_numpy(new_data).float()

[0109] # predict

[0110] prediction = model(new_data_tensor)

[0111] print(f"Prediction result: {prediction}")

[0112] For the above model, you can also use a combination of regular updates and online updates to further fine-tune the model. Regular updates refer to retraining the model with newly collected data at regular intervals; online updates refer to fine-tuning the model with new data whenever it arrives during the model operation.

[0113] It is understandable that other machine learning algorithms such as random forest algorithm can also be used as a framework to train the fault monitoring and diagnosis model. For example, based on the random forest algorithm, the status data and fault conditions of various equipment of the vehicle under different driving conditions in historical periods are collected as samples to generate a training set, which is input into the model for training, and initial parameters are set, such as the number of decision trees is 100, the maximum depth is 8, etc. The model performance is evaluated by cross-validation and other methods, and the parameters such as the number of decision trees and the maximum depth are continuously adjusted to observe the performance of the model on the validation set until a good performance indicator is achieved.

[0114] According to the embodiments of the present disclosure, the fault monitoring and diagnosis model can quickly and accurately determine the fault type and provide corresponding solutions, thereby improving maintenance efficiency and reducing the time the vehicle is down due to faults.

[0115] S130, analyzing the real-time data through the fuse life prediction model to predict the life status of the fuse; if the predicted life status of the fuse is not good, sending a fuse replacement reminder.

[0116] Specifically:

[0117] The current load and temperature changes of the fuse can be monitored in real time by installing current sensors and temperature sensors near the fuse. For example, when the vehicle starts, a large number of electrical devices start at the same time, which may cause excessive instantaneous current. The current sensor can accurately measure the current passing through the fuse, and the temperature sensor can detect the temperature changes of the fuse. If the current exceeds the rated current of the fuse or the temperature rises abnormally, it may indicate that the fuse has potential risks.

[0118] Through the fuse life prediction model, the fuse life status is analyzed according to the current load and temperature changes in the real-time data and the vehicle operating conditions, and the possibility of the fuse failing is predicted; when the fuse status is detected to be poor, a warning message is displayed on the display screen, and additional audio-visual warnings can be provided through buzzers, flashing lights, etc., and relevant personnel can be remotely notified through text messages, APP push, etc., so that timely measures can be taken.

[0119] Traditional fuse monitoring relies solely on simple threshold judgments (e.g., if the current exceeds the rated current, it is considered likely to blow), while machine learning algorithms can learn a large amount of fuse life data under different working conditions. By analyzing the real-time monitored current and temperature data, combined with threshold analysis and trend prediction, the fuse life status can be more accurately judged.

[0120] More specifically, the current sensor can use a Hall effect sensor, the temperature sensor can use a thermistor sensor, and the fuse life prediction model can use a random forest algorithm; in addition to the current load and temperature change data and vehicle operating condition data, some other features can also be extracted to improve the prediction ability of the model; for example, the current change rate, temperature change trend, vehicle mileage and other features can be calculated. Multiple thresholds can be set to determine the state of the fuse. For example, the upper and lower thresholds of the current load are set. When the current exceeds the upper threshold or is lower than the lower threshold, the fuse is considered to be at risk. At the same time, the temperature safety range threshold is set. When the temperature exceeds this range, the fuse is also considered to have problems. Time series analysis methods, such as moving average method, exponential smoothing method, etc., can also be used to predict the change trend of current and temperature. If the current and temperature show an upward trend and are predicted to exceed the threshold in the future, then the fuse life state is considered to be poor.

[0121] The fuse life prediction model is obtained through the following training:

[0122] The current load and temperature change data of the fuse at each historical moment and the operating condition data of the vehicle are used as the input data of the model, and the fuse life status corresponding to the current load and temperature change data of the fuse at each historical moment and the operating condition data of the vehicle are used as labels to generate a training set;

[0123] The training set is used to train the model and update the parameters until a fuse life prediction model is generated.

[0124] For example:

[0125] Monitor the current load and temperature changes of the fuse in real time. At the same time, obtain the vehicle's operating data through the vehicle's bus, such as driving speed, engine speed, battery voltage, etc. Over a period of time, record the current load, temperature changes and vehicle operating data at different times, as well as the actual life status of the fuse.

[0126] Assume that the following data is collected:

[0127] Historical moment 1: The current load is 8A, the temperature is 30°C, the vehicle speed is 50km / h, the engine speed is 2000rpm, the battery voltage is 12.5V, and the fuse life status is good.

[0128] Historical moment 2: The current load is 10A, the temperature is 35°C, the vehicle speed is 60km / h, the engine speed is 2500rpm, the battery voltage is 12.3V, and the fuse life status is fair.

[0129] Historical moment 3: The current load is 12A, the temperature is 40°C, the vehicle speed is 70km / h, the engine speed is 3000rpm, the battery voltage is 12.1V, and the fuse life status is poor.

[0130] The current load, temperature change and vehicle operating condition data of the fuse at the historical moment collected are used as input data, and the corresponding fuse life status is used as a label to generate a training set.

[0131] The data of the above three historical moments are organized into the following form:

[0132] Input data: [[8, 30, 50, 2000, 12.5], [10, 35, 60, 2500, 12.3], [12, 40,70, 3000, 12.1]]

[0133] Tags: [good, average, poor]

[0134] The training set is trained using the random forest algorithm. The training set is randomly divided into multiple subsets. Each subset is used to train a decision tree. The prediction results of each decision tree are integrated by voting to obtain the final prediction result. During the training process, the parameters of the algorithm, such as the number of decision trees and the depth of the tree, are continuously adjusted to improve the accuracy of the model until the required fuse life prediction model is generated. The specific training process can be as follows:

[0135] import numpy as np

[0136] from sklearn.ensemble import RandomForestClassifier

[0137] import smtplib

[0138] from email.mime.text import MIMEText

[0139] import requests

[0140] # Historical data

[0141] data = [[8, 30, 50, 2000, 12.5], [10, 35, 60, 2500, 12.3], [12, 40,70, 3000, 12.1]]

[0142] labels = ['good', 'average', 'poor']

[0143] # Convert to numpy array

[0144] X = np.array(data)

[0145] y = np.array(labels)

[0146] # Create a random forest classifier

[0147] clf = RandomForestClassifier()

[0148] # Train the model

[0149] clf.fit(X, y) .

[0150] Assume that the current sensor measures the current through the fuse to be 11A, the temperature sensor detects the temperature of the fuse to be 38°C, the vehicle speed is 65km / h, the engine speed is 2800rpm, and the battery voltage is 12.2V. These data are input into the fuse life prediction model. The model predicts that the fuse life status is fair to poor. The result is notified to relevant personnel through a warning message on the display, SMS, and APP push. The specific process can be as follows:

[0151] # Real-time data

[0152] new_data = [[11, 38, 65, 2800, 12.2]]

[0153] # Make predictions

[0154] prediction = clf.predict(new_data)

[0155] # Display warning message

[0156] if prediction == 'bad':

[0157] print("The fuse life is not good, please check it in time!")

[0158] else:

[0159] print(f"Fuse life status: {prediction}")

[0160] # SMS Notification

[0161] def send_sms(message):

[0162] print(f"SMS notification: {message}")

[0163] # APP Push Notification

[0164] def send_app_push(message):

[0165] print(f"APP push notification: {message}")

[0166] if prediction == 'bad':

[0167] sms_message = "The fuse life is not good, please check it in time!"

[0168] app_push_message = "Fuse life warning: poor condition, please handle as soon as possible."

[0169] send_sms(sms_message)

[0170] send_app_push(app_push_message).

[0171] It is understandable that other machine learning algorithms such as neural network algorithms can also be used as a framework to train the fuse life prediction model. Taking the neural network algorithm as an example, the training set is input into the model for training, and the initial structure is set, such as the input layer has 4 neurons, corresponding to the fuse current, temperature, driving speed, and acceleration; the hidden layer has 10 neurons; the output layer has 3 neurons, corresponding to the fuse life status of good, general, and poor. The weights and biases of the model are continuously adjusted through the back propagation algorithm, so that the model can accurately predict the life status of the fuse. After multiple training and optimization, the required fuse life prediction model is obtained.

[0172] According to the embodiments of the present disclosure, the fuse life prediction model is trained with the current load and temperature change data of the fuse at historical moments and the vehicle operating condition data, so that the life status of the fuse can be predicted more accurately, and a replacement plan can be arranged in advance to avoid circuit failures caused by sudden failure of the fuse.

[0173] S140, if it is detected that the fault is cleared or the fuse is replaced, the power supply is automatically restored.

[0174] Specifically, for a circuit that stops supplying power due to a fault, the relevant parameters are re-tested. If the monitored parameters return to the normal range and remain stable, it is confirmed that the fault has been cleared. For a circuit that stops supplying power due to replacing a fuse, the status of the fuse is tested. If it works normally and the fuse life is good, it is confirmed that the fuse has been successfully replaced. Once it is confirmed that the fault has been cleared or the fuse has been replaced, power supply is automatically restored so that the device can resume normal operation.

[0175] For example, when a circuit branch triggers the protection mechanism due to a short circuit, the identification of the circuit branch and the abnormal current during the short circuit are recorded, and the resistance, current and other parameters of the circuit branch are re-tested at regular intervals to determine whether it has returned to normal and whether normal power supply has been restored.

[0176] It should be noted that for safety reasons, a delayed power supply time can be set for automatic power supply restoration after a fault. When the system detects that the fault has been cleared or the fuse has been replaced, it may not automatically restore the power supply immediately, but instead start a timer. The timer can set different delay times based on different fault types and equipment importance. If the maintenance method corresponding to the equipment fault type is dangerous, the delay time can be set to 1 minute or even longer. This can give maintenance personnel enough time to stabilize the equipment status and keep a safe distance. It also provides operators with a time window for observation and confirmation, ensuring that no unexpected situations occur after power is restored, further improving the safety and reliability of the system.

[0177] More specifically, automatic power restoration can be achieved through the following devices: intelligent relays, contactors, programmable logic controller (PLC) and power switch combination, intelligent circuit breakers, etc. Among them:

[0178] When the timer ends, the smart relay receives a control signal, automatically closes the contacts and restores power. The smart relay can be programmed to achieve different delay time settings and can communicate with other monitoring devices to ensure that power is restored in a safe manner.

[0179] A contactor is a switching device used to control high-power circuits. A contactor with a timer can start the timer after receiving a signal that a fault has been cleared or a fuse has been replaced. When the timer ends, the contactor closes and power is restored.

[0180] PLC can receive signals from various sensors and control according to preset logic. At the same time, PLC can adjust the delay time setting according to different fault types and equipment importance. When the fault is detected to be cleared or the fuse is replaced, PLC receives the control signal and starts the timer. After the timer ends, PLC outputs the control signal to control the power switch to close and restore power supply.

[0181] The intelligent circuit breaker has functions such as overcurrent protection and short-circuit protection, and can interact with other devices through the communication interface. When a circuit fault occurs, the intelligent circuit breaker will automatically trip and cut off the circuit; when it is detected that the fault is cleared or the fuse is replaced, the intelligent circuit breaker receives a control signal and starts a timer. After the timer ends, the intelligent circuit breaker automatically closes and restores power supply.

[0182] According to the embodiments of the present disclosure, power supply is automatically restored after strict confirmation of fault clearance and fuse replacement completion, thereby improving the use efficiency of the vehicle.

[0183] Another embodiment is provided below to further illustrate the above implementation.

[0184] Assume that a vehicle is equipped with a CAN bus for data transmission, multiple sensors are installed for monitoring device status, and an intelligent power management box is also equipped. The intelligent power management box applies the intelligent power management method 100 provided in the embodiment of the present disclosure. The real-time data of multiple devices collected are as follows:

[0185] The first set of data: battery voltage: 345V, motor current: 95A, interior temperature: 24°C, driving speed: 55km / h, acceleration: 1.5m / s², fuse current: 7.5A, fuse temperature: 32°C.

[0186] The second set of data: battery voltage: 330V, motor current: 110A, interior temperature: 26°C, driving speed: 50km / h, acceleration: 1m / s², fuse current: 8.2A, fuse temperature: 35°C.

[0187] The third set of data: battery voltage: 355V, motor current: 80A, interior temperature: 25°C, driving speed: 60km / h, acceleration: 2m / s², fuse current: 7.8A, fuse temperature: 33°C.

[0188] Set the normal data range threshold: battery voltage range is 340V - 360V, and the normal motor current range is 80A-100A.

[0189] For the first set of data, all parameters are within the normal range, and it is judged that there is no fault at this time.

[0190] For the second set of data, the motor current exceeded the normal range. The model further analyzed the fault data to predict the fault type. Combined with the vehicle operating data and historical fault patterns, the model determined that the overload fault might be caused by a sudden increase in motor load.

[0191] For the third set of data, all parameters are within the normal range, and it is judged that there is no fault at this time.

[0192] For the overload fault determined by the second set of data, the corresponding solution is matched in the preset fault solution library: check whether there is a mechanical fault in the motor drive system that causes increased resistance or whether there is an abnormality in other equipment that causes increased motor load. At the same time, consider adjusting the motor control parameters to reduce the current.

[0193] The fuse current and temperature data and vehicle operating condition data in the three sets of data are input into the fuse life prediction model.

[0194] For the first set of data, the fuse life status is predicted to be good after analysis.

[0195] For the second set of data, although there is a fault in the motor, the changes in fuse current and temperature are relatively small, and the model predicts that the fuse life status is fair.

[0196] For the third set of data, the fuse life status is predicted to be good.

[0197] Since the poor fuse life status is not predicted in any of the three sets of data, no fuse replacement reminder will be sent.

[0198] The fault recovery detection interval is set to 10 minutes. For the overload fault determined by the second set of data, the power recovery delay time is 1 minute. Check every 10 minutes to confirm whether the fault has been cleared. If cleared, power supply will be automatically restored after 1 minute to allow the equipment to resume normal operation.

[0199] According to the embodiments of the present disclosure, the following beneficial effects are achieved:

[0200] On the basis of reducing vehicle wiring harnesses by multiplexing multiple buses, the fault monitoring and diagnosis model is used to quickly and accurately determine the fault type and provide corresponding solutions, which effectively improves maintenance efficiency and reduces maintenance time. At the same time, the fuse life prediction model is used to warn of the fuse life status in advance, avoiding circuit problems caused by fuse failure, and further enhancing the safety and reliability of vehicle power management. On the basis of the above, the function of automatically restoring power supply after fault clearing or fuse replacement is added, so that the vehicle can quickly return to normal working state, and also makes the entire power management system more intelligent.

[0201] In summary, the coordinated use of multiple bus multiplexing, fault monitoring and diagnosis model, fuse life prediction model and self-recovery function effectively improves the performance and reliability of the vehicle.

[0202] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present disclosure is not limited by the order of the actions described, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0203] The above is an introduction to the method embodiment. The following is a further explanation of the scheme disclosed in the present invention through an apparatus embodiment.

[0204] Figure 2 FIG. 4 shows a block diagram of an intelligent power management device according to an embodiment of the present disclosure; Figure 2 As shown, the intelligent power management device 200 may include:

[0205] An acquisition unit 210 is used to acquire real-time data of multiple devices based on multiple bus multiplexing;

[0206] The fault diagnosis and display unit 220 is used to analyze the real-time data through the fault monitoring and diagnosis model to determine whether there is a fault, and if so, predict the fault type; match the corresponding fault solution according to the fault type to facilitate maintenance;

[0207] The fuse monitoring unit 230 is used to analyze the real-time data through the fuse life prediction model to predict the life status of the fuse; if the predicted life status of the fuse is not good, a fuse replacement reminder is sent;

[0208] The self-recovery unit 240 is used to automatically restore power supply if it is detected that the fault is cleared or the fuse is replaced.

[0209] Understandably, Figure 2 Each unit in the shown intelligent power management device 200 has the function of implementing each step in the intelligent power method 100 provided in the embodiment of the present disclosure, and can achieve its corresponding technical effect. The specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment. For the convenience and conciseness of the description, it will not be repeated here.

[0210] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.

[0211] Figure 3A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown.

[0212] like Figure 3 As shown, electronic device 300 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0213] The electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a ROM 302 or a computer program loaded from a storage unit 308 into a RAM 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An I / O interface 305 is also connected to the bus 304.

[0214] A number of components in the electronic device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0215] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as method 100. For example, in some embodiments, the method 100 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the method 100 described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to perform the method 100 in any other appropriate manner (e.g., by means of firmware).

[0216] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0217] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0218] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0219] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0220] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0221] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0222] The present disclosure also provides a vehicle, to which the intelligent power management method 100 is applied.

[0223] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0224] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An intelligent power management method, characterized in that: The method comprises: Based on multiplex bus multiplexing, obtain real-time data of multiple devices; The real-time data is analyzed by the fault monitoring and diagnosis model to determine whether there is a fault, and if so, the fault type is predicted; the corresponding fault solution is matched according to the fault type to facilitate maintenance; wherein the fault monitoring and diagnosis model is obtained by the following training: using the data of the equipment at each historical moment and the working condition data of the vehicle as the input data of the model, using the data of the equipment at each historical moment and the fault state and type corresponding to the working condition data of the vehicle as the label, and generating a training set; using the training set to train the model and update the parameters until the fault monitoring and diagnosis model is generated; The real-time data is analyzed by a fuse life prediction model to predict the life status of the fuse; if the predicted life status of the fuse is not good, a fuse replacement prompt is sent; wherein the fuse life prediction model is obtained by the following training: The current load and temperature change data of the fuse at each historical moment and the operating condition data of the vehicle are used as the input data of the model, and the fuse life status corresponding to the current load and temperature change data of the fuse at each historical moment and the operating condition data of the vehicle are used as labels to generate a training set; the training set is used to train the model and update the parameters until the fuse life prediction model is generated; If it is detected that the fault has been cleared or the fuse has been replaced, the power supply will be automatically restored; including: for the circuit that has stopped power supply due to a fault, if it is detected that the parameters have returned to the normal range and remain stable, it is confirmed that the fault has been cleared, the timer is started, and the power supply is automatically restored after the timing ends; for the circuit that has stopped power supply due to fuse replacement, the status of the fuse is detected. If it is working normally and the fuse life status is good, it is confirmed that the fuse has been replaced successfully and the power supply is automatically restored.

2. The method according to claim 1, characterized in that The method of acquiring real-time data of multiple devices based on multiple bus multiplexing includes: Based on multiplexed bus multiplexing, one or more shared buses are used to obtain real-time data from multiple devices.

3. The method according to claim 1, characterized in that The real-time data is analyzed by the fault monitoring and diagnosis model to determine whether there is a fault, and if so, the fault type is predicted; Match the corresponding fault solution according to the fault type to facilitate maintenance, including: By using the fault monitoring and diagnosis model, the real-time data is compared with normal data to determine whether the real-time data exceeds a preset threshold. If the real-time data exceeds the preset threshold, it is determined that a fault exists, and the fault type is predicted based on the fault data. According to the fault type, the corresponding fault solution is matched in the preset fault solution library to facilitate maintenance.

4. An intelligent power management device, characterized in that: The intelligent power management device comprises: An acquisition unit, used for acquiring real-time data of multiple devices based on multiple bus multiplexing; A fault diagnosis and display unit is used to analyze the real-time data through a fault monitoring and diagnosis model to determine whether there is a fault, and if so, predict the type of fault; match the corresponding fault solution according to the fault type to facilitate maintenance; wherein the fault monitoring and diagnosis model is obtained through the following training: using the data of the equipment at each historical moment and the working condition data of the vehicle as the input data of the model, using the data of the equipment at each historical moment and the fault state and type corresponding to the working condition data of the vehicle as labels, and generating a training set; using the training set to train the model and update the parameters until the fault monitoring and diagnosis model is generated; The fuse monitoring unit is used to analyze the real-time data through a fuse life prediction model to predict the life state of the fuse; if the predicted life state of the fuse is not good, a fuse replacement prompt is sent; wherein the fuse life prediction model is obtained through the following training: The current load and temperature change data of the fuse at each historical moment and the operating condition data of the vehicle are used as the input data of the model, and the fuse life status corresponding to the current load and temperature change data of the fuse at each historical moment and the operating condition data of the vehicle are used as labels to generate a training set; the training set is used to train the model and update the parameters until the fuse life prediction model is generated; The self-recovery unit is used to automatically restore power supply if it is detected that the fault has been cleared or the fuse has been replaced; including: for a circuit that has stopped power supply due to a fault, if it is detected that the parameters have returned to the normal range and remain stable, it is confirmed that the fault has been cleared, and the timer is started. After the timer ends, the power supply is automatically restored; for a circuit that has stopped power supply due to fuse replacement, the status of the fuse is detected. If it works normally and the fuse life status is good, it is confirmed that the fuse has been replaced successfully and the power supply is automatically restored.

5. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 3.

6. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to make a computer execute the method according to any one of claims 1-3.

7. A vehicle, characterized in that: The vehicle applies the method according to any one of claims 1 to 3.

Images