An online monitoring system for the health status of batteries in ring main unit
By deploying an online monitoring system for battery health status in the ring network cabinet, using SOC algorithm and neural network model, accurate monitoring and alarm of battery status is achieved, and the problem of failure to detect battery performance problems in the existing technology is solved, and the problem of improving the Battery reliability and monitoring stability.
Patent Information
- Application Number
- CN202210996756.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-08-19
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2042-08-19
AI Technical Summary
The batteries in the ring network cabinet are prone to failures such as expansion, terminal rust, acid-swelling corrosion in complex operating environments. The existing detection methods cannot detect battery performance problems in a timely manner, which affects service life and operation and maintenance costs.
Design an online monitoring system for the health status of a ring cabinet, including a monitoring terminal and a monitoring server, collect voltage, current, and temperature data, use SOC algorithm to estimate the battery status, and combine the neural network model to process data and alarm trigger threshold setting. Realize real-time detection and dynamic monitoring.
It realizes accurate online identification of battery internal resistance, capacity and other parameters, timely warning and operation and maintenance instructions, ensures the reliability and monitoring stability of the battery, and reduces operation and maintenance costs.
Smart Images

Figure CN115407216B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of ring main unit detection technology, and in particular to an online monitoring system for the health status of a ring main unit battery. Background Art
[0002] The current operating environment of ring main units is relatively complex. The temperature reaches 45℃ to 55℃ in summer and below 0℃ in winter. The humidity is high in spring and autumn. The batteries cannot be in a stable and good operating environment. They are prone to expansion, terminal rust, acid corrosion, etc. There are a large number of potential fault hazards and the operation and maintenance costs are high.
[0003] The main means of battery detection is to detect voltage. During normal operation of the ring network cabinet, the battery is in a floating charge state and the voltage is generally normal. However, there are actual problems with the performance of the battery, and it cannot be discharged normally or cannot meet the backup power supply requirements after the normal power supply fails.
[0004] Currently, a large number of ring main units are used in power distribution networks. There are also many types of batteries inside the ring main units, and the consistency between battery cells is poor. Improper management after grouping will cause hidden dangers of malfunction, which will in turn affect the service life of the battery and bring huge challenges to batch application management. Summary of the invention
[0005] In order to overcome the deficiencies in the above-mentioned prior art, the present invention provides an online monitoring system for the health status of batteries in a ring main unit, comprising: a monitoring terminal and a monitoring server; the monitoring terminal is arranged inside each ring main unit, monitors the status information of the batteries inside the ring main unit, and transmits the status information to the monitoring server;
[0006] The monitoring terminal includes: a communication module, a master control module and a slave control module;
[0007] The slave control module is used to collect the voltage, current and temperature data information of the battery and transmit the collected data information to the master control module;
[0008] The main control module is equipped with a battery parameter online identification unit and a data processing unit;
[0009] The battery parameter online identification unit is used to compare and judge the voltage, current and temperature data information of the battery respectively to determine whether they exceed the threshold value. If they exceed the threshold value, the exceeding threshold value information is sent to the monitoring server;
[0010] The data processing unit is used to estimate the SOC value of the battery based on the SOC algorithm when the battery is in a charging or discharging state;
[0011] Real-time detection of battery current I, estimation of battery SOC value at the current time by using Ampere integration method, acquisition of battery charge and discharge capacity, and deriving battery attenuation state by charge and discharge capacity and SOC value;
[0012] The voltage conversion rate in each time period is also obtained according to the working current I and the working current V of the battery, and the conversion efficiency of the battery energy and the internal resistance R of the battery are obtained;
[0013] The data processing unit also uploads the battery status information to the monitoring server through the communication module.
[0014] It should be further explained that the monitoring server includes: a battery status transceiver module, a data conversion module and a data processing module;
[0015] The battery status receiving module is used to receive the battery status information sent by the monitoring terminal, and form each battery status information into a battery data set;
[0016] The data conversion module is used to configure the data in the battery data set into a battery data feature vector and a data identifier;
[0017] The data processing module is used to perform training using the battery data feature vector in the battery data set as a learning model, and output the data identifier corresponding to the battery data as the learning model;
[0018] Determine an alarm trigger threshold of the battery data based on a weight value corresponding to a feature vector of the battery data after training;
[0019] The battery status transceiver module configures the alarm trigger threshold to the monitoring terminal as the battery parameter judgment alarm trigger threshold within a preset time period; when the battery parameter exceeds the alarm trigger threshold, an alarm is issued.
[0020] It should be further explained that the data processing unit of the main control module configures a battery data set of the battery in use in each ring network cabinet; the data processing unit judges the alarm trigger threshold based on the battery parameters within a preset time period sent by the battery status transceiver module, and an alarm is issued if the threshold is exceeded.
[0021] It should be further explained that the data processing module receives the battery parameters in each battery parameter receiving time period and configures them into a battery data set;
[0022] The data processing module also determines the fluctuation range of the received battery parameters within each battery parameter receiving time period.
[0023] If the fluctuation range of the battery parameters received within a unit time is less than or equal to a first preset fluctuation threshold, the battery parameters are received from a preset time point and a battery data set is configured.
[0024] It should be further explained that if the fluctuation range of the battery parameter received within a unit time is greater than the first preset fluctuation threshold, then the average value of the battery parameter received within the unit time is calculated to determine whether the average value is within the second preset fluctuation threshold;
[0025] If yes, configure the battery data set with the average value of the battery parameter;
[0026] If it is not within the second preset fluctuation threshold range, it is judged as abnormal data and an alarm is issued.
[0027] It should be further explained that the data processing module receives battery parameters in each battery parameter receiving time period, compares the ratio with the battery parameters obtained in the adjacent time period, and determines whether the ratio exceeds the comparison threshold. If so, it compares the ratio with the battery parameters obtained in the previous N time periods to determine whether the ratio exceeds the comparison threshold. If both exceed the threshold, it is determined that the current battery parameters are abnormal and an alarm is issued.
[0028] It should be further explained that the data processing module is also used to configure the battery parameters of the battery data set into a preset neural network unit, each neuron first inputs a weighted accumulation value and then inputs an activation function as the output value of the neuron, and performs forward propagation to obtain a battery parameter score;
[0029] The battery parameter score is input into the error function loss function, and compared with the expected value to get the error. If there are multiple values, they are summed. The degree of recognition is determined by the error.
[0030] Then through back propagation and reverse derivation, the error function and each activation function in the neural network are required to minimize the error to determine the gradient vector of the battery data in the battery data set;
[0031] Each weight is adjusted through the gradient vector, and the battery parameter score is configured to make the error tend to 0 or converge.
[0032] Repeat the above process until the set number of times or the average value of the loss error no longer drops to the lowest point to obtain the weight value corresponding to the battery data feature vector.
[0033] It should be further explained that the battery voltage acquisition of the slave control module is realized through the LTC6803-1 chip;
[0034] The slave module has a built-in 12-bit ADC, voltage reference data, high voltage input multiplexer and serial interface.
[0035] The slave control module measures the voltage of 12 batteries connected in series with a measurement error within 0.25% and completes the measurement of all batteries within 13ms.
[0036] It should be further explained that the slave control module is also equipped with a voltage detection channel, and the effective value input of the voltage detection channel is 250mV;
[0037] It is also equipped with a current channel, which integrates a gain programmable amplifier, and the maximum effective value of the input level can be 250mV or 50mV;
[0038] The modulator of CS5460A is also configured with oversampling principle, which can suppress high-frequency signal noise and filter the signal.
[0039] It should be further explained that the communication module uses CAN communication for data transmission;
[0040] The communication module realizes the communication connection between the master control module and the slave control module, and also realizes the communication connection between the master control module and the monitoring server;
[0041] The communication module is equipped with two CAN ports, namely CANA and CANB, with an operating voltage of 3.3V. CANA is used to receive current and voltage information sent from the master control module and the slave control module, and CANB is used to send estimated status parameters to the monitoring server;
[0042] The communication module is equipped with SN65HVD230 chip.
[0043] It can be seen from the above technical solutions that the present invention has the following advantages:
[0044] The ring main unit battery health status online monitoring system of the present invention can accurately identify the battery internal resistance, capacity and other parameters online, accurately judge the battery health status locally and timely preset instructions for operation and maintenance, and upload early warning data signals. This device ensures the reliability of the ring main unit battery as a backup power supply.
[0045] The present invention can detect the battery current I in real time, estimate the battery SOC value at the current time by using the Ampere integral method, obtain the battery charge and discharge power, and obtain the battery attenuation state by the charge and discharge power and the SOC value. The monitoring server can obtain each battery status information to form a battery data set, and use the battery data set to train through a preset battery status learning model to optimize the value of the battery data feature vector. Based on the optimized battery data feature vector, the alarm trigger threshold is quantified and configured to the monitoring terminal, thereby realizing dynamic monitoring of the battery status. In this way, the stability of the monitoring process and the comprehensiveness of the data are improved, and the monitoring status is guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.
[0047] Figure 1 This is a schematic diagram of the online monitoring system for the health status of the battery in the ring main unit;
[0048] Figure 2 This is a schematic diagram of an embodiment of an online monitoring system for the health status of batteries in a ring main unit. DETAILED DESCRIPTION
[0049] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0050] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.
[0051] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.
[0052] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present invention. However, those skilled in the art will appreciate that the technical solution of the present invention can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring various aspects of the present invention.
[0053] The present invention provides an online monitoring system for the health status of batteries in a ring main unit. Figures 1 to 2 As shown, it includes: a monitoring terminal 2 and a monitoring server 1; the monitoring terminal 2 is arranged inside each ring main unit, monitors the status information of the battery inside the ring main unit, and transmits the status information to the monitoring server 1;
[0054] The monitoring terminal 2 includes: a communication module 3, a main control module 4 and a slave control module 5;
[0055] The slave control module 5 is used to collect the voltage, current and temperature data information of the battery, and transmit the collected data information to the master control module 4; the master control module 4 is equipped with a battery parameter online identification unit and a data processing unit;
[0056] The battery parameter online identification unit is used to compare and judge the voltage, current and temperature data information of the battery respectively to judge whether they exceed the threshold value. If they exceed the threshold value, the exceeding threshold value information is sent to the monitoring server 1;
[0057] The data processing unit is used to estimate the SOC value of the battery based on the SOC algorithm when the battery is in a charging or discharging state;
[0058] Real-time detection of battery current I, estimation of battery SOC value at the current time by using Ampere integration method, acquisition of battery charge and discharge capacity, and deriving battery attenuation state by charge and discharge capacity and SOC value;
[0059] The voltage conversion rate in each time period is also obtained based on the working current I and the working current V of the battery, and the conversion efficiency of the battery energy and the internal resistance R of the battery are obtained.
[0060] The data processing unit also uploads the battery status information to the monitoring server 1 through the communication module 3 .
[0061] Here, SOC is defined as State of Charge, or SOC for short, which refers to the available state of the remaining charge in the battery, which can be described by the following proportional formula: SOC = (remaining charge / rated charge) * 100%, so that relevant information about the battery can be obtained. In addition, the battery energy conversion efficiency and the internal resistance R of the battery can be measured. In this way, knowing the current state of the battery is convenient for tracking the state of the battery, and the battery can be adjusted and maintained based on the on-site use environment.
[0062] As an embodiment of the present invention, the monitoring server 1 includes: a battery status transceiver module, a data conversion module and a data processing module;
[0063] The battery status receiving module is used to receive the battery status information sent by the monitoring terminal 2, and form each battery status information into a battery data set;
[0064] The data conversion module is used to configure the data in the battery data set into a battery data feature vector and a data identifier;
[0065] Among them, the battery data feature vector is a form of battery status information compiled, and in the subsequent model training process, it is used as the input battery status data of the battery status learning model; the data identifier is the monitoring result of the output battery status information, and the result can be over-threshold or not over-threshold. Of course, in the battery status model training process, it can be used as the battery status information output of the battery status learning model.
[0066] The data processing module is used to perform training using the battery data feature vector in the battery data set as a learning model, and output the data identifier corresponding to the battery data as the learning model;
[0067] Determine an alarm trigger threshold of the battery data based on a weight value corresponding to a feature vector of the battery data after training;
[0068] The battery status transceiver module configures the alarm trigger threshold to the monitoring terminal 2 as the battery parameter judgment alarm trigger threshold within a preset time period; an alarm is issued when the battery parameter exceeds the alarm trigger threshold.
[0069] The training method may be to configure the battery parameters of the battery data set into a preset neural network unit, first input a value of each neuron for weighted accumulation, then input an activation function as the output value of the neuron, and perform forward propagation to obtain a battery parameter score;
[0070] The battery parameter score is input into the error function loss function, and compared with the expected value to get the error. If there are multiple values, they are summed. The degree of recognition is determined by the error.
[0071] Then through back propagation and reverse derivation, the error function and each activation function in the neural network are required to minimize the error to determine the gradient vector of the battery data in the battery data set;
[0072] Each weight is adjusted through the gradient vector, and the battery parameter score is configured to make the error tend to 0 or converge. The SGD algorithm can be used here to perform.
[0073] Repeat the above process until the set number of times or the average value of the loss error no longer drops to the lowest point to obtain the weight value corresponding to the battery data feature vector.
[0074] Of course, in the present invention, the battery status data set can be extracted by using the chi-square feature selection algorithm.
[0075] The purpose here is to train the learning model through the battery state model training of the present invention. The battery data feature vector is input into the battery state learning model, and the battery state training result can be output. During the training process of the battery data feature vector, the loss function is derived based on the maximum likelihood estimation. Then, the loss of the battery data training result and the expected result of the battery data during the training process is calculated according to the battery data loss function, which can also be a preset result, and the weight value corresponding to the feature vector in the battery data learning model is adjusted for the purpose of reducing the loss.
[0076] Furthermore, based on the weight value corresponding to the battery data feature vector after training, the alarm trigger threshold of the battery data is determined; the battery status transceiver module configures the alarm trigger threshold to the monitoring terminal 2 as the battery parameter judgment alarm trigger threshold within a preset time period; when the battery parameter exceeds the alarm trigger threshold, an alarm is issued.
[0077] The present invention will describe a mobile terminal implementing various embodiments of the present invention with reference to the accompanying drawings. In the subsequent description, suffixes such as "module", "component" or "unit" used to represent elements are used only to facilitate the description of the embodiments of the present invention, and they themselves have no specific meaning. Therefore, "module" and "component" can be used interchangeably.
[0078] The monitoring terminal and the monitoring server may include a wireless communication unit, an audio / video input unit, a user input unit, a sensing unit, an output unit, a memory, an interface unit, a controller, a power supply unit, etc. Wireless communication may be adopted.
[0079] The data processing of the monitoring terminal and the monitoring server can be implemented by using at least one of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a processor, a controller, a microcontroller, a microprocessor, and an electronic unit designed to perform the functions described herein. In some cases, such an implementation can be implemented in a controller. For software implementation, implementations such as processes or functions can be implemented with separate software modules that allow execution of at least one function or operation. The software code can be implemented by a software application (or program) written in any appropriate programming language, and the software code can be stored in a memory and executed by a controller.
[0080] As an implementation mode of the present invention, the data processing unit of the main control module configures a battery data set of the battery in use in each ring network cabinet; the data processing unit judges the alarm trigger threshold of the battery parameters within a preset time period based on the battery parameters sent by the battery status transceiver module, and an alarm is issued if the threshold is exceeded.
[0081] The battery data set may include the battery's voltage, current, temperature data, internal resistance R, and battery degradation state.
[0082] Of course, in the battery data set, a data set can be used to configure the battery voltage into a data set based on the time sequence, so that each parameter has a data set.
[0083] During the configuration of the battery data set, the data processing module receives the battery parameters in each battery parameter receiving time period and configures the battery data set;
[0084] The data processing module further determines the fluctuation range of the battery parameters received within each battery parameter receiving time period, and if the fluctuation range of the battery parameters received within a unit time is less than or equal to a first preset fluctuation threshold, the battery parameters are received from a preset time point, and a battery data set is configured;
[0085] If the fluctuation range of the battery parameter received within a unit time is greater than the first preset fluctuation threshold, then calculating the average value of the battery parameter received within the unit time, and determining whether the average value is within the second preset fluctuation threshold;
[0086] If yes, configure the battery data set with the average value of the battery parameter;
[0087] If it is not within the second preset fluctuation threshold range, it is judged as abnormal data and an alarm is issued. In this way, the single battery data can meet the preset requirements.
[0088] As an implementation mode of the present invention, the data processing module receives the battery parameters in each battery parameter receiving time period, compares the battery parameters obtained in the adjacent time period, and determines whether the ratio exceeds the comparison threshold. If exceeded, the data processing module compares the battery parameters obtained in the previous N time periods to determine whether the ratio exceeds the comparison threshold. If both exceed the threshold, it is determined that the current battery parameters are abnormal and an alarm is issued. The number of N time periods can be set according to monitoring needs, and the length of the time period can be set according to actual needs.
[0089] As an implementation mode of the present invention, the main control module can be configured with DSP28335, and the online identification of battery internal resistance, capacity and other parameters will be implemented by the least squares method in the DSP28335 engineering board, the SOC estimation will be implemented by the PI observer algorithm in the engineering board, and the health status will adopt the threshold values of parameters such as internal resistance and capacity.
[0090] The chip selected for the slave control module is LTC6803-1, which has a built-in 12-bit ADC, a precision voltage reference, a high voltage input multiplexer and a serial interface. It can measure the voltage of up to 12 series-connected batteries, with a maximum total measurement error of 0.25%, and can complete the measurement of all batteries in a system in 13ms. Multiple LTC6803-1 chips can be connected in series through a unique level-shifting serial interface to increase the number of battery cell voltage detections.
[0091] The current detection of the slave control module uses CS5460A, and the maximum effective value input of the voltage channel of this chip is 250mV. The current channel integrates a gain programmable amplifier (PGA), and the maximum effective value of the input level can be 250mV or 50mV. Therefore, when the current signal is sampled through the shunt resistor to form a full-scale 75mV voltage signal, the input to this chip can meet the conditions. Since the modulator of CS5460A adopts the oversampling principle, it has a strong suppression of high-frequency signal noise, so the input signal does not need to be complicatedly filtered.
[0092] The communication module uses CAN communication for data transmission; the communication module realizes the communication connection between the master control module and the slave control module, and also realizes the communication connection between the master control module and the monitoring server;
[0093] The communication module is equipped with MS320F28335 control board. The communication module has two CAN ports, namely CANA and CANB, with an operating voltage of 3.3V. CANA is used to receive current and voltage information sent from the high-voltage box and the slave control box, and CANB is used to send estimated state parameters to the PC host computer. The chip selected in the design is the SN65HVD230 chip produced by TI. This chip is a special CAN transceiver with a high communication rate, good anti-electromagnetic interference ability, and can achieve real-time and high-reliability serial communication.
[0094] CAN communication is used to realize the communication between the master control module and the slave control module. Voltage, current, SOC and other parameter detection quantities require data to be transmitted and saved, and the communication is guaranteed to be real-time and reliable. The CAN bus serial communication protocol can meet the requirements.
[0095] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.
[0096] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. An online monitoring system for the health status of batteries in a ring main unit, characterized in that: include: Monitoring terminal and monitoring server; The monitoring terminal is set inside each ring main unit to monitor the status information of the battery inside the ring main unit and transmit the status information to the monitoring server; The monitoring terminal includes: a communication module, a master control module and a slave control module; The slave control module is used to collect the voltage, current and temperature data information of the battery and transmit the collected data information to the master control module; The main control module is equipped with a battery parameter online identification unit and a data processing unit; The battery parameter online identification unit is used to compare and judge the voltage, current and temperature data information of the battery respectively to determine whether they exceed the threshold value. If they exceed the threshold value, the exceeding threshold value information is sent to the monitoring server; The data processing unit is used to estimate the SOC value of the battery based on the SOC algorithm when the battery is in a charging or discharging state; Real-time detection of battery current I, estimation of battery SOC value at the current time by using Ampere integration method, acquisition of battery charge and discharge capacity, and deriving battery attenuation state by charge and discharge capacity and SOC value; The voltage conversion rate in each time period is also obtained according to the working current I and the working current V of the battery, and the conversion efficiency of the battery energy and the internal resistance R of the battery are obtained; The data processing unit also uploads the battery status information to the monitoring server through the communication module.
2. The ring main unit battery health status online monitoring system according to claim 1 is characterized in that: The monitoring server includes: a battery status transceiver module, a data conversion module and a data processing module; The battery status receiving module is used to receive the battery status information sent by the monitoring terminal, and form each battery status information into a battery data set; The data conversion module is used to configure the data in the battery data set into a battery data feature vector and a data identifier; The data processing module is used to perform training using the battery data feature vector in the battery data set as a learning model, and output the data identifier corresponding to the battery data as the learning model; Determine an alarm trigger threshold of the battery data based on a weight value corresponding to a feature vector of the battery data after training; The battery status transceiver module configures the alarm trigger threshold to the monitoring terminal as the battery parameter judgment alarm trigger threshold within a preset time period; when the battery parameter exceeds the alarm trigger threshold, an alarm is issued.
3. The ring main unit battery health status online monitoring system according to claim 2 is characterized in that: The data processing unit of the main control module configures the battery data set under the usage status of the battery in each ring network cabinet; the data processing unit judges the alarm trigger threshold of the battery parameters within a preset time period sent by the battery status transceiver module to judge the battery parameters, and an alarm is issued if the threshold is exceeded.
4. The ring main unit battery health status online monitoring system according to claim 2 is characterized in that: The data processing module receives the battery parameters in each battery parameter receiving time period and configures them into a battery data set; The data processing module also determines the fluctuation range of the received battery parameters within each battery parameter receiving time period. If the fluctuation range of the battery parameters received within a unit time is less than or equal to a first preset fluctuation threshold, the battery parameters are received from a preset time point and a battery data set is configured.
5. The ring main unit battery health status online monitoring system according to claim 4 is characterized in that: If the fluctuation range of the battery parameter received within a unit time is greater than the first preset fluctuation threshold, then calculating the average value of the battery parameter received within the unit time, and determining whether the average value is within the second preset fluctuation threshold; If yes, configure the battery data set with the average value of the battery parameter; If it is not within the second preset fluctuation threshold range, it is judged as abnormal data and an alarm is issued.
6. The ring main unit battery health status online monitoring system according to claim 2 is characterized in that: The data processing module receives the battery parameters in each battery parameter receiving time period, compares them with the battery parameters obtained in the adjacent time period, and determines whether the ratio exceeds the comparison threshold. If so, it compares them with the battery parameters obtained in the previous N time periods to determine whether the ratio exceeds the comparison threshold. If both exceed the threshold, it is determined that the current battery parameters are abnormal and an alarm is issued.
7. The ring main unit battery health status online monitoring system according to claim 2 is characterized in that: The data processing module is also used to configure the battery parameters of the battery data set into a preset neural network unit, each neuron first inputs a weighted accumulation value and then inputs an activation function as the output value of the neuron, and performs forward propagation to obtain a battery parameter score; The battery parameter score is input into the error function loss function, and compared with the expected value to get the error. If there are multiple values, they are summed. The degree of recognition is determined by the error. Then through back propagation and reverse derivation, the error function and each activation function in the neural network are required to minimize the error to determine the gradient vector of the battery data in the battery data set; Each weight is adjusted through the gradient vector, and the battery parameter score is configured to adjust the error to 0 or convergence trend; Repeat the above process until the set number of times or the average value of the loss error no longer drops to the lowest point to obtain the weight value corresponding to the battery data feature vector.
8. The ring main unit battery health status online monitoring system according to claim 1 is characterized in that: The battery voltage collection of the slave control module is realized through the LTC6803-1 chip; The slave module has a built-in 12-bit ADC, voltage reference data, high voltage input multiplexer and serial interface. The slave control module measures the voltage of 12 batteries connected in series with a measurement error within 0.25% and completes the measurement of all batteries within 13ms.
9. The ring main unit battery health status online monitoring system according to claim 1 is characterized in that: The slave control module is also equipped with a voltage detection channel, and the effective value input of the voltage detection channel is 250mV; It is also equipped with a current channel, which integrates a gain programmable amplifier, and the maximum effective value of the input level can be 250mV or 50mV; The modulator of CS5460A is also configured with oversampling principle, which can suppress high-frequency signal noise and filter the signal.
10. The ring main unit battery health status online monitoring system according to claim 1, characterized in that: The communication module uses CAN communication for data transmission; The communication module realizes the communication connection between the master control module and the slave control module, and also realizes the communication connection between the master control module and the monitoring server; The communication module is equipped with two CAN ports, namely CANA and CANB, with an operating voltage of 3.3V. CANA is used to receive current and voltage information sent from the master control module and the slave control module, and CANB is used to send estimated status parameters to the monitoring server; The communication module is equipped with SN65HVD230 chip.
