Power supply state detection method and device, intelligent terminal, power van and storage medium

Abstract

The invention discloses a power supply state detection method and device, an intelligent terminal, a power van and a storage medium, and relates to the technical field of electric power Internet of Things. Historical load data of a power supply area and power generation performance data of the power emergency power supply vehicle are acquired through a vehicle-mounted intelligent terminal on the power emergency power supply vehicle; inputting the historical load data into a load prediction model based on the multistage echo state network to obtain a load prediction curve; inputting the power generation performance data into an operation state monitoring model based on a gated cycle unit array to obtain a performance prediction value; and determining a power supply state value according to the load prediction curve and the performance prediction value. A power supply state value is determined by combining a load prediction model based on a multi-stage ESN and an operation state monitoring model based on a GRU array, the power supply state of the power emergency power supply vehicle can be monitored in real time, so that a power distribution main station platform accurately and efficiently regulates and commands the power emergency power supply vehicle to rescue and grab disasters, and the power emergency guarantee capability is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power internet of things, and in particular to a power supply state detection method and device, an intelligent terminal, a power supply vehicle and a storage medium. BACKGROUND

[0002] With the rapid development of society and the increasing demand for electricity, power emergency power supply vehicles, as an efficient and reliable power supply means, have received more and more attention and recognition.

[0003] The power emergency power supply vehicle can provide stable and reliable power output, and is also equipped with an intelligent monitoring system and an automatic control function. However, there is still a problem of insufficient digitalization, which cannot monitor the power supply state of the power emergency power supply vehicle in real time, resulting in the inability to accurately and efficiently control and command the power emergency power supply vehicle to rescue and fight disasters, causing waste of valuable power resources and a great impact on the emergency support capability of power. SUMMARY

[0004] The present application provides a power supply state detection method, device, intelligent terminal, power supply vehicle and storage medium to solve the problem that the existing power emergency power supply vehicle cannot monitor the power supply state of the power emergency power supply vehicle in real time, resulting in the inability to accurately and efficiently control and command the power emergency power supply vehicle to rescue and fight disasters.

[0005] In a first aspect, the present application provides a power supply state detection method applied to a vehicle-mounted intelligent terminal, comprising:

[0006] Collecting historical load data of a power supply area and power generation performance data of a power emergency power supply vehicle;

[0007] Inputting the historical load data into a load prediction model based on a multi-level echo state network to obtain a load prediction curve;

[0008] Inputting the power generation performance data into an operation state monitoring model based on a gated recurrent unit array to obtain a performance prediction value;

[0009] Determining a power supply state value according to the load prediction curve and the performance prediction value.

[0010] Further, the load prediction model based on the multi-level echo state network comprises an input module, a multi-level echo state network module and an output module.

[0011] The multi-level echo state network module is composed of a plurality of echo state network units, and the input value of each echo state network unit is the output value of the previous level echo state network unit.

[0012] Further, the input module is configured to perform feature processing on the input historical load data to obtain load feature data, and input the load feature data into the multi-level echo state network module;

[0013] The multi-level echo state network module is configured to process the load feature data to obtain a final output value, and input the final output value into the output module;

[0014] The output module is configured to map the final output value to a load prediction value of the power supply area, and determine a load prediction curve according to the load prediction value at each time point.

[0015] Further, the method further comprises: optimizing model parameters in the load prediction model based on the multi-level echo state network based on a particle swarm algorithm.

[0016] Further, the operating state monitoring model based on the gated recurrent unit array comprises: an input layer, a gated recurrent unit array, and a fully connected layer; the gated recurrent unit array is composed of n*m gated recurrent units, wherein each feature item in the n feature items of the power generation performance data corresponds to a group of gated recurrent units with a sliding window of m;

[0017] The input layer is configured to extract the n feature items of the power generation performance data;

[0018] The gated recurrent unit array is configured to process the n feature items to obtain a prediction value;

[0019] The fully connected layer is configured to map the prediction value output by the gated recurrent unit array to a performance prediction value of the electric power emergency power supply vehicle.

[0020] Further, after determining the power supply state value according to the load prediction curve and the performance prediction value, the method further comprises:

[0021] In a case where the power supply state value continuously falls below a threshold value within a preset time, the performance prediction value and the power supply state value are reported to a power distribution master station platform, so that the power distribution master station platform schedules the electric power emergency power supply vehicle.

[0022] In a second aspect, an embodiment of the present application provides a power supply state detection device applied to a vehicle-mounted intelligent terminal, the device comprising:

[0023] A data acquisition module is configured to acquire historical load data of a power supply area and power generation performance data of an electric power emergency power supply vehicle;

[0024] A load prediction module is configured to input the historical load data into a load prediction model based on a multi-level echo state network to obtain a load prediction curve;

[0025] a performance prediction module, configured to input the power generation performance data into a running state monitoring model based on a gated recurrent unit array to obtain a performance prediction value;

[0026] a power supply state determination module, configured to determine a power supply state value according to the load prediction curve and the performance prediction value.

[0027] In a third aspect, an embodiment of the present application provides an intelligent terminal, which comprises:

[0028] at least one processor;

[0029] and a memory in communication connection with the at least one processor;

[0030] wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the power supply state detection method according to any one of the embodiments of the present application.

[0031] In a fourth aspect, an embodiment of the present application provides an electric power emergency power supply vehicle, which comprises: the vehicle-mounted intelligent terminal according to any one of the embodiments of the present application, a convergence unit installed in a power generation compartment of the electric power emergency power supply vehicle, a generator set controller, a sensor assembly and a vehicle chassis;

[0032] The vehicle-mounted intelligent terminal is in communication with the convergence unit, the generator set controller and the vehicle chassis respectively, and the convergence unit is in communication with the sensor assembly;

[0033] The vehicle-mounted intelligent terminal performs state control on the generator set controller based on the power supply state value.

[0034] In a fifth aspect, an embodiment of the present application provides a computer readable storage medium, which stores computer instructions, and the computer instructions are used to enable a processor to implement the power supply state detection method according to any one of the embodiments of the present application when executed.

[0035] The technical scheme of the embodiment of the present application collects historical load data of a power supply area and power generation performance data of the power emergency generator truck through the vehicle-mounted intelligent terminal on the power emergency generator truck; inputs the historical load data into a load prediction model based on a multi-level echo state network to obtain a load prediction curve; inputs the power generation performance data into an operation state monitoring model based on a gated recurrent unit array to obtain a performance prediction value; and determines the power supply state value according to the load prediction curve and the performance prediction value. The power supply state value is determined in combination with the load prediction model based on the multi-level ESN and the operation state monitoring model based on the GRU array, the power supply state of the power emergency generator truck can be monitored in real time, so that the power distribution master station platform can accurately and efficiently control and command the power emergency generator truck to rescue and fight disasters, and the power emergency guarantee capability is improved, and the problem that the existing power emergency generator truck cannot monitor the power supply state of the power emergency generator truck in real time, resulting in the inability to accurately and efficiently control and command the power emergency generator truck to rescue and fight disasters is solved.

[0036] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0038] Figure 1 A flow chart of a power supply state detection method provided for the first embodiment of the present application;

[0039] Figure 2 A flow chart of a power supply state detection method provided for the second embodiment of the present application;

[0040] Figure 3 A structural schematic diagram of a load prediction model based on a multi-level echo state network provided for the second embodiment of the present application;

[0041] Figure 4 A structural schematic diagram of a single gated recurrent unit of a gated recurrent unit array provided for the second embodiment of the present application;

[0042] Figure 5 A structural schematic diagram of a power supply state detection device provided for the second embodiment of the present application;

[0043] Figure 6 A structural schematic diagram of a vehicle-mounted intelligent terminal for realizing the power supply state detection method of the present application;

[0044] Figure 7 A structure schematic diagram of the power emergency power supply vehicle according to the embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the personnel in the technical field better understand the present application scheme, the technical scheme in the embodiment of the present application will be described clearly and completely in the following with reference to the drawings in the embodiment of the present application. Obviously, the described embodiment is only a part of the embodiment of the present application, not all. Based on the embodiment in the present application, all other embodiments obtained by the person skilled in the art without creative labor should belong to the protection scope of the present application.

[0046] It should be noted that the terms "include" and "have" and any variation thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover the inclusions that are not exclusive, for example, the processes, methods, systems, products or devices that include a series of steps or units do not have to be limited to the clearly listed steps or units, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0047] Embodiment one

[0048] Figure 1 A flow chart of a power supply state detection method provided by the embodiment one of the present application, the embodiment can be applicable to the case of detecting the power supply state of the power emergency power supply vehicle, the method can be executed by a power supply state detection device, the power supply state detection device can be realized in the form of hardware and / or software, and the power supply state detection device can be configured in the vehicle-mounted intelligent terminal. As shown in the figure, the method comprises: Figure 1

[0049] S110, collecting historical load data of a power supply area and power generation performance data of the power emergency power supply vehicle.

[0050] The power supply area is a basic power supply unit in the power distribution network, usually refers to the area composed of a power distribution transformer and the lines, equipment and users supplied by the transformer, is an important part of the low-voltage distribution network and directly faces the terminal users for power supply.

[0051] The historical load data of the power supply area can be understood as the load data of the power supply area in the past time, for example, can include active load data and reactive load data. The power generation performance data of the power emergency power supply vehicle can include: generator set parameters (such as rated power, frequency and voltage output, etc.), real-time operation parameters (such as output current, reactive / active power, frequency fluctuation, etc.), energy storage parameters (such as battery capacity and charge / discharge power, etc.).

[0052] ​Exemplarily, the power generation performance data of the power emergency generator vehicle is acquired by monitoring the acquisition device or the sensor, and the historical load data of the power supply station area is acquired by communicating with the master station platform.

[0053] In S120, the historical load data is input into the load prediction model based on the multi-level echo state network to obtain a load prediction curve.

[0054] The load prediction model is trained based on the multi-level echo state network and is used to predict the load prediction curve of the power supply station area in a period of time. Due to the use scenario of the power emergency generator vehicle, it is generally a short-term load prediction curve.

[0055] The multi-level echo state network (ESN) includes a hierarchical reservoir pool composed of randomly sparsely connected hidden layers. Through the hierarchical reservoir pool, load features of different time scales can be extracted, for example, the first-level ESN captures short-term fluctuations (hour level), the second-level ESN models medium-term trends (day level), and the nth-level ESN learns long-term cycles (week / month level). The basic idea of ESN is to generate a complex dynamic space that changes with input from the reservoir pool. When this state space is complex enough, the internal states can be used to linearly combine the corresponding outputs as needed.

[0056] Specifically, the historical load data stored in the database is used to construct training samples, and the load prediction model based on the multi-level echo state network is trained. The historical load data in the past preset time period is input into the load prediction model based on the multi-level echo state network to capture the dependency of the historical load data and predict the load change, and a load prediction curve is obtained.

[0057] In S130, the power generation performance data is input into the operation state monitoring model based on the gated recurrent unit array to obtain a performance prediction value.

[0058] The performance prediction value can include the maximum power supply capacity (such as the rated power of the generator set) and the predicted output of renewable energy (such as wind power and photovoltaic power).

[0059] The gated recurrent unit array (GRU) introduces a gating mechanism, effectively alleviates training difficulties such as gradient disappearance and gradient explosion by controlling the flow and retention of information, and has better long-term dependency modeling capability.

[0060] Specifically, the power generation performance data is input into the operation state monitoring model based on the gated recurrent unit array, multi-dimensional features of the power generation performance data are extracted through parallel GRU branches, and a performance prediction value is output through a fusion layer.

[0061] S140, determining the power supply state value according to the load prediction curve and the performance prediction value.

[0062] The power supply state value S(t) can be a Boolean value (0 or 1 indicates whether the power supply is normal) or a continuous value (such as a percentage or a margin). If the power supply state value is a margin state value, it can be defined as S(t) = power supply capacity(t) - load demand(t) ; if S(t) ≥ 0, the power supply is normal; if S(t) < 0, the power supply is insufficient. If the power supply state value is a percentage state value, if S(t) ≥ 100%, the power supply is sufficient; if S(t) < 100%, the power supply has a gap.

[0063] Specifically, for each time point t, the load demand is read from the load prediction curve, the power supply capacity is read from the performance prediction value, and the power supply state value is calculated according to the load demand and the power supply capacity.

[0064] The technical scheme of the embodiment of the application acquires historical load data of a power supply area and power generation performance data of a power emergency power supply vehicle through a vehicle-mounted intelligent terminal on the power emergency power supply vehicle; inputs the historical load data into a load prediction model based on a multi-level echo state network to obtain a load prediction curve; inputs the power generation performance data into a running state monitoring model based on a gated recurrent unit array to obtain a performance prediction value; and determines a power supply state value according to the load prediction curve and the performance prediction value. The power supply state value is determined in combination with the load prediction model based on the multi-level ESN and the running state monitoring model based on the GRU array, so that the power supply state of the power emergency power supply vehicle can be monitored in real time, so that the power distribution master station platform can accurately and efficiently control and command the power emergency power supply vehicle to rescue and fight disasters, and the power emergency support capability can be improved.

[0065] Embodiment two

[0066] Figure 2 A flowchart of a power supply state detection method provided for the second embodiment of the application, the embodiment further refines the model structure of the load prediction model of the multi-level echo state network and the model structure of the running state monitoring model based on the gated recurrent unit array on the basis of the above-mentioned embodiment. As shown in the figure, Figure 2 the method comprises:

[0067] S210, acquiring historical load data of a power supply area and power generation performance data of a power emergency power supply vehicle.

[0068] S220, inputting the historical load data into a load prediction model based on a multi-level echo state network to obtain a load prediction curve.

[0069] In an optional embodiment, the load prediction model based on the multi-level echo state network comprises an input module, a multi-level echo state network module and an output module.

[0070] The multi-level echo state network module is composed of multiple echo state network units, and the input value of each echo state network unit is the output value of the previous level echo state network unit.

[0071] The input module is used to perform feature processing on the input historical load data to obtain load feature data, and input the load feature data into the multi-level echo state network.

[0072] The multi-level echo state network is used to process the load characteristic data, obtain the final output value, and input the final output value into the output module;

[0073] The output module is used to map the final output value to the load forecast value of the power supply area, and to determine the load forecast curve based on the load forecast value at each time.

[0074] For example, Figure 3 This is a schematic diagram of a load prediction model based on a multi-level echo state network, provided in Embodiment 2 of the present invention. Figure 3 As shown, the load forecasting model based on the multi-level echo state network includes: an input module, a multi-level echo state network (ESN) module (i.e., a reserve pool), and an output module.

[0075] A multi-level ESN module consists of k ESN units, where each ESN unit takes the output value of the previous ESN unit as its input. The structural formula of a multi-level ESN module is as follows:

[0076]

[0077] Among them, W in W is the input weight matrix from the input module to the multi-level ESN module. out W is the connection weight matrix from the storage pool to the output module, and W is the internal weight matrix of the multi-level ESN module, W = [W1 W2 W]. k ]; o k The connection state between two levels of ESN units is represented by f(·), which is the activation function of neurons within a multi-level ESN module, typically the sigmoid function. out (·) represents the activation function of the output layer neurons, x k (t) represents the state value of the neuron in the reservoir at time t, x k (t+1) represents the state value of the neurons inside the reservoir at time t+1, y(t+1) represents the final output value of the output module at time t+1, and u(t+1) represents the input parameters of the input module at time t+1.

[0078] W in W is generated before training and will not change during training; only W is updated during training.out .

[0079] In an optional embodiment, the model parameters in the load forecasting model based on the multi-level echo state network are trained based on a particle swarm algorithm.

[0080] The working process of training the multi-level ESN model based on the particle swarm optimization (PSO) optimization algorithm to obtain the load forecasting model based on the multi-level echo state network is as follows:

[0081] Step 1: dividing the collected load data samples into a training set and a test set, normalizing the training set and the test set, and creating a multi-level ESN model;

[0082] Step 2: initializing the PSO optimization algorithm parameters, limiting the value range of the initial learning rate in the multi-level ESN model, and initializing the speed and position of individuals in different dimensions of the PSO population;

[0083] Step 3: establishing a particle fitness function through a mean square normalized error performance function of the multi-level ESN;

[0084] Step 4: calculating the local optimal value and the global optimal value;

[0085] Step 5: calculating the updated particle speed and position;

[0086] Step 6: determining whether the maximum number of iterations is reached, and if so, outputting the optimal parameters, otherwise returning to step 4;

[0087] Step 7: obtaining the optimal number of hidden layer neurons and the initial learning rate parameters, and initializing the multi-level ESN model;

[0088] Step 8: training the multi-level ESN model based on the training set;

[0089] Step 9: performing data de-normalization, analyzing the classification results of the model, and calculating the training accuracy;

[0090] Step 10: evaluating the multi-level ESN model based on the test set.

[0091] S230, inputting the power generation performance data into the operation state monitoring model based on the array of gated recurrent units to obtain a performance prediction value.

[0092] In an optional embodiment, the operation state monitoring model based on the array of gated recurrent units comprises an input layer, an array of gated recurrent units, and a fully connected layer; the array of gated recurrent units is composed of n×m gated recurrent units, wherein each feature item in n feature items of the power generation performance data corresponds to a group of gated recurrent units with a sliding window of m;

[0093] The input layer is configured to extract n feature items of the power generation performance data;

[0094] The gated recurrent unit array is configured to process the n feature items to obtain a predicted value;

[0095] The fully connected layer is configured to map the predicted value output by the gated recurrent unit array to a performance predicted value of the power emergency power supply vehicle.

[0096] Exemplarily, Figure 4 A structure diagram of a single gated recurrent unit in a gated recurrent unit array provided for Embodiment Two of the present application is shown in FIG. 2. Figure 4 As shown in FIG. 1, the operation state monitoring model based on the gated recurrent unit GRU array includes an input layer, a gated recurrent unit GRU array and a fully connected layer.

[0097] The GRU array is composed of n*m GRU units. Each type of feature item of the power generation performance data corresponds to a group of GRU units with a sliding window of m. Then, the GRU units corresponding to n types of feature items form a m*n GRU matrix.

[0098] The present embodiment performs lightweight pruning on the conventional GRU unit, and defines a lightweight (LW-GRU, LightWeighted GRU) structure formula as follows:

[0099]

[0100] wherein y t-1 is the hidden layer output of the previous GRU, y t is the output of the current GRU, x t is the power generation performance data input to the current GRU, σ is a Sigmoid function, z t is the update gate of the GRU, y t ' is the updated intermediate state, U z is the weight of the update gate, W y is the weight of the intermediate state, b z is a bias.

[0101] The fully connected layer maps the predicted value output by the GRU array to the performance predicted value of the power emergency power supply vehicle through a SoftMax classifier.

[0102] S240, determining a power supply state value according to the load prediction curve and the performance predicted value.

[0103] S250, in the case that the power supply state value in the preset time is continuously lower than the threshold value, reporting the performance predicted value and the power supply state value to a power distribution master station platform, so as to enable the power distribution master station platform to schedule the power emergency power supply vehicle.

[0104] The threshold value can be understood as a set early warning value or expected value.

[0105] Specifically, in the case that the power supply state value in the preset time is continuously lower than the threshold value, it indicates that the power supply state of the power emergency power supply vehicle cannot meet the load demand of the power supply station area, at this time, the performance prediction value and the power supply state value are reported to the power distribution master station platform, and the power distribution master station platform schedules the power emergency power supply vehicle to ensure the normal power supply of the power supply station area.

[0106] The technical scheme of the embodiment of the application acquires historical load data of a power supply station area and power generation performance data of a power emergency power supply vehicle, inputs the historical load data into a load prediction model based on a multi-level echo state network to obtain a load prediction curve, inputs the power generation performance data into an operation state monitoring model based on a gated recurrent unit array to obtain a performance prediction value, determines a power supply state value according to the load prediction curve and the performance prediction value, and reports the performance prediction value and the power supply state value to a power distribution master station platform in the case that the power supply state value in a preset time is continuously lower than a threshold value, so that the power distribution master station platform schedules the power emergency power supply vehicle. The load prediction model based on the multi-level ESN and the operation state monitoring model based on the GRU array determine the power supply state value, which can monitor the power supply state of the power emergency power supply vehicle in real time, and timely report to the power distribution master station platform in the case of power supply shortage, so that the power distribution master station platform accurately and efficiently controls and commands the power emergency power supply vehicle to rescue and fight disasters, and improves the power emergency guarantee capability.

[0107] Embodiment three

[0108] Figure 5 The embodiment three of the application provides a structural schematic diagram of a power supply state detection device. As shown in the figure, Figure 5 The device comprises a data acquisition module 310, a load prediction module 320, a performance prediction module 330 and a power supply state determination module 340, wherein:

[0109] The data acquisition module 310 is used for acquiring historical load data of a power supply station area and power generation performance data of a power emergency power supply vehicle.

[0110] The load prediction module 320 is used for inputting the historical load data into a load prediction model based on a multi-level echo state network to obtain a load prediction curve.

[0111] The performance prediction module 330 is used for inputting the power generation performance data into an operation state monitoring model based on a gated recurrent unit array to obtain a performance prediction value.

[0112] The power supply state determination module 340 is used for determining a power supply state value according to the load prediction curve and the performance prediction value.

[0113] The power supply state detection device provided by the embodiment of the application is applied to a vehicle-mounted intelligent terminal on an emergency power supply vehicle, historical load data of a power supply area and power generation performance data of the emergency power supply vehicle are collected, the historical load data is input into a load prediction model based on a multi-level echo state network to obtain a load prediction curve, the power generation performance data is input into an operation state monitoring model based on a gated recurrent unit array to obtain a performance prediction value, and a power supply state value is determined according to the load prediction curve and the performance prediction value. The power supply state value is determined in combination with the load prediction model based on the multi-level echo state network and the operation state monitoring model based on the GRU array, the power supply state of the emergency power supply vehicle can be monitored in real time, and the power distribution master station platform can accurately and efficiently control and command the emergency power supply vehicle to rescue and fight disasters, thereby improving the power emergency support capability.

[0114] Optionally, the load prediction model based on the multi-level echo state network comprises an input module, a multi-level echo state network module and an output module.

[0115] The multi-level echo state network module is composed of a plurality of echo state network units, and the input value of each echo state network unit is the output value of the previous level echo state network unit.

[0116] Optionally, the input module is configured to perform feature processing on the input historical load data to obtain load feature data, and input the load feature data into the multi-level echo state network module.

[0117] The multi-level echo state network module is configured to process the load feature data to obtain a final output value, and input the final output value into the output module.

[0118] The output module is configured to map the final output value to a load prediction value of the power supply area, and determine a load prediction curve according to the load prediction value at each time point.

[0119] Optionally, the device further comprises:

[0120] A model training module is configured to optimize model parameters in the load prediction model based on the multi-level echo state network based on a particle swarm algorithm.

[0121] Optionally, the operation state monitoring model based on the gated recurrent unit array comprises an input layer, a gated recurrent unit array and a fully connected layer, and the gated recurrent unit array is composed of n×m gated recurrent units, wherein each feature item in n feature items of the power generation performance data corresponds to a group of gated recurrent units with a sliding window of m.

[0122] The input layer is configured to extract n feature items of the power generation performance data.

[0123] The gating recurrent unit array is used for processing the n feature items to obtain a predicted value;

[0124] The full connection layer is used for mapping the predicted value output by the gating recurrent unit array into a performance predicted value of the power emergency power supply vehicle.

[0125] Optionally, the device further comprises:

[0126] An information reporting module is configured to, after determining the power supply state value according to the load prediction curve and the performance predicted value, report the performance predicted value and the power supply state value to a power distribution master station platform in a case where the power supply state value is continuously lower than a threshold value within a preset time, so that the power distribution master station platform schedules the power emergency power supply vehicle.

[0127] The power supply state detection device provided in the embodiments of the present application can execute the power supply state detection method provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0128] Embodiment four

[0129] Figure 6 A structural schematic diagram of a vehicle-mounted intelligent terminal 10 that can be used to implement the embodiments of the present application is shown. The vehicle-mounted intelligent terminal is intended to represent an intelligent terminal deployed on a power emergency power supply vehicle. 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 application described and / or claimed herein.

[0130] As shown in Figure 6 The vehicle-mounted intelligent terminal 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is in communication connection with the at least one processor 11, wherein the memory stores a computer program that can be executed by the at least one processor. The processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the vehicle-mounted intelligent terminal 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0131] A plurality of components in the in-vehicle intelligent terminal 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, and the like; an output unit 17, such as various types of displays, a speaker, and the like; a storage unit 18, such as a magnetic disk, an optical disk, and the like; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 19 allows the in-vehicle intelligent terminal 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0132] The processor 11 can be various general and / or special-purpose processing components having processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, and the like. The processor 11 performs various methods and processes described above, such as the power supply state detection method.

[0133] In some embodiments, the power supply state detection method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the in-vehicle intelligent terminal 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded onto the RAM 13 and executed by the processor 11, one or more steps of the power supply state detection method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the power supply state detection method by any other appropriate means, such as by means of firmware.

[0134] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0135] In some embodiments, the power supply status detection method can be implemented as a computer program, which is tangibly embodied in a computer program product, the computer program, when executed by a processor, implements the power supply status detection method of the present application, and the computer program product can be understood as a software product which mainly realizes the solution thereof through the computer program. The computer program for implementing the method of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, so that the computer programs, when executed by the processor, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, partially on a machine as a separate software package and partially on a remote machine, or entirely on a remote machine or server.

[0136] In the context of the present application, a computer-readable storage medium can be a tangible medium which can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0137] To provide for interaction with a user, the systems and techniques described here can be implemented on a vehicle intelligent terminal having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the vehicle intelligent terminal. Other kinds of devices can be used to provide for interaction with a user as well; for example, 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, speech, or tactile input.

[0138] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can 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), a blockchain network, and the Internet.

[0139] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0140] Embodiment five

[0141] Figure 7 A structural schematic diagram of an electric power emergency power supply vehicle 1 that can be used to implement an embodiment of the present application is shown. As shown, the electric power emergency power supply vehicle includes a vehicle-mounted intelligent terminal 10, a convergence unit 20 installed in a power generation compartment of the electric power emergency power supply vehicle, a generator set controller 30, a sensor assembly 40, and a vehicle chassis 50. Figure 7

[0142] The vehicle-mounted intelligent terminal 10 communicates with the convergence unit 20, the generator set controller 30, and the vehicle chassis 50, respectively; and the convergence unit 20 communicates with the sensor assembly 40.

[0143] The vehicle-mounted intelligent terminal 10 performs state control on the generator set controller 30 based on a power supply state value.

[0144] Specifically, the sensor assembly 40 is installed inside the electric power emergency power supply vehicle 1, and can include, for example, a temperature sensor, a humidity sensor, a smoke sensor, and the like, for collecting the temperature and humidity, noise, and smoke concentration inside the generator set cabin, and for monitoring the working environment inside the generator set cabin in real time. The vehicle-mounted intelligent terminal 10 can communicate with the convergence unit 20 installed in the power generation compartment through RS-485, and the convergence unit 20 can communicate with the sensor assembly 40 through low-power wireless communication, without wiring for the sensors inside the cabin. ​

[0145] The vehicle-mounted intelligent terminal 10 can also communicate with the generator set controller 30 through RS-485, collect generator set data, and combine with power supply area load data to perform state monitoring and remote state control on the generator set, such as start control, stop control, and emergency stop control.

[0146] The vehicle-mounted intelligent terminal 10 can also communicate with the vehicle chassis 50 through the CAN bus. The vehicle-mounted intelligent terminal 10 has an OBD interface through which relevant data of the vehicle chassis 50 is collected, and has functions of vehicle test data analysis, chassis state analysis, and maintenance state analysis.

[0147] In an optional embodiment, the power emergency power supply vehicle 1 further comprises an Ethernet power supply network camera connected with the vehicle-mounted intelligent terminal 10 through an RJ45, and a handheld game device connected through a Bluetooth communication interface.

[0148] The vehicle-mounted intelligent terminal 10 further comprises a positioning module and a wireless communication module. The vehicle-mounted intelligent terminal 10 communicates with a power distribution master station platform through the wireless communication module. The power distribution master station platform can include a cloud master station, a video platform, an irrelevant platform, and a power distribution autonomous station, etc.

[0149] It should be understood that the various forms of flow shown above can be used to reorder, add or delete steps. For example, the steps described in the present application can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, and the present application is not limited herein.

[0150] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for detecting power supply status, characterized in that, Applied to in-vehicle intelligent terminals, the method includes: Collect historical load data of the power supply area and power generation performance data of the emergency power supply vehicle; The historical load data is input into a load forecasting model based on a multi-level echo state network to obtain a load forecasting curve. The power generation performance data is input into the operation status monitoring model based on the gated cyclic unit array to obtain the performance prediction value; The power supply status value is determined based on the load prediction curve and the performance prediction value.

2. The method according to claim 1, characterized in that, The load prediction model based on a multi-level echo state network includes: an input module, a multi-level echo state network module, and an output module; The multi-level echo state network module is composed of multiple echo state network units, and the input value of each echo state network unit is the output value of the previous level echo state network unit.

3. The method according to claim 2, characterized in that, The input module is used to perform feature processing on the input historical load data to obtain load feature data, and input the load feature data into the multi-level echo state network module. The multi-level echo state network module is used to process the load characteristic data, obtain the final output value, and input the final output value into the output module; The output module is used to map the final output value to the load forecast value of the power supply area, and to determine the load forecast curve based on the load forecast value at each time.

4. The method according to any one of claims 2-3, characterized in that, The method further includes optimizing the model parameters in the load prediction model based on the multi-level echo state network using the particle swarm optimization algorithm.

5. The method according to claim 1, characterized in that, The operational status monitoring model based on the gated cyclic unit array includes: an input layer, a gated cyclic unit array, and a fully connected layer; the gated cyclic unit array consists of n×m gated cyclic units, wherein each of the n feature items of the power generation performance data corresponds to a set of gated cyclic units with a sliding window of m; The input layer is used to extract n feature terms from the power generation performance data; The gated cyclic unit array is used to process the n feature terms to obtain the predicted value; The fully connected layer is used to map the predicted values ​​output by the gated cyclic unit array to the performance prediction values ​​of the power emergency power supply vehicle.

6. The method according to claim 1, characterized in that, After determining the power supply status value based on the load forecast curve and the performance forecast value, the method further includes: If the power supply status value remains below a threshold for a preset period of time, the performance prediction value and the power supply status value will be reported to the power distribution master station platform so that the power distribution master station platform can dispatch the power emergency power supply vehicle.

7. A power supply status detection device, characterized in that, The device, used in in-vehicle intelligent terminals, includes: The data acquisition module is used to collect historical load data of the power supply area and power generation performance data of the emergency power supply vehicle; The load forecasting module is used to input the historical load data into a load forecasting model based on a multi-level echo state network to obtain a load forecasting curve. The performance prediction module is used to input the power generation performance data into the operation status monitoring model based on the gated cyclic unit array to obtain the performance prediction value; The power supply status determination module is used to determine the power supply status value based on the load prediction curve and the performance prediction value.

8. A vehicle-mounted intelligent terminal, characterized in that, Deployed on a power emergency power supply vehicle, the on-board intelligent terminal includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the power supply status detection method according to any one of claims 1-6.

9. A power emergency power supply vehicle, characterized in that, include: The vehicle-mounted intelligent terminal, the aggregation unit, the generator set controller, the sensor assembly, and the vehicle chassis installed in the power generation compartment of the power emergency power vehicle as described in claim 8; The vehicle-mounted intelligent terminal communicates with the aggregation unit, the generator set controller, and the vehicle chassis, respectively; the aggregation unit communicates with the sensor assembly; The vehicle-mounted intelligent terminal performs status control on the generator set controller based on the power supply status value.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the power supply status detection method according to any one of claims 1-6.

Images