A detection device and system for an emergency lighting backup battery

Abstract

The application provides a detection device and system for an emergency lighting backup battery, a controller of the device switches the emergency lighting lamp body from mains power to the backup battery power at a preset interval, and then calls a pre-constructed battery health state evaluation model to predict current time series data and voltage time series data, generate an SOH value of the backup battery and a backup battery replacement suggestion based on the SOH value, and upload the suggestion to a terminal through a wireless module, thereby solving the inconvenience of manually testing a large number of emergency lighting backup batteries in factories, shopping malls or residential buildings.

Description

Technical Field

[0001] This invention relates to the field of emergency lighting, and in particular to a detection device and system for backup batteries in emergency lighting. Background Technology

[0002] Currently, some fire departments stipulate that independent emergency lighting fixtures must be inspected regularly to ensure that the batteries can maintain illumination for at least n hours (e.g., 2 hours) after a power outage. Traditional inspection methods require manual operation, such as turning off the power or pressing a test button, and then observing whether the light works properly. This method is not only time-consuming and labor-intensive, but also cannot predict when the batteries will need to be replaced. In particular, some factories, shopping malls, or residential buildings are equipped with many emergency lighting devices, and conducting regular manual inspections would be a massive undertaking.

[0003] In view of the above, this application is hereby submitted. Summary of the Invention

[0004] This invention discloses a testing device and system for backup batteries in emergency lighting, aiming to solve the inconvenience of manually testing the large number of backup batteries for emergency lighting in factories, shopping malls, or residential buildings.

[0005] The first embodiment of the present invention provides a detection device for a backup battery of an emergency lighting system, comprising: an adapter disposed between the emergency lighting body and the backup battery, wherein the adapter includes a controller disposed therein, a wireless module electrically connected to the radio frequency terminal of the controller, and a current acquisition unit and a voltage acquisition unit electrically connected to the input terminal of the controller;

[0006] The controller is configured to execute a computer program stored therein to perform the following steps:

[0007] At preset intervals, the emergency lighting unit is switched from mains power to backup battery power, and backup battery discharge data collected by current acquisition unit and voltage acquisition unit is acquired, wherein the discharge data includes current timing data and voltage timing data;

[0008] A pre-built battery health status assessment model is invoked, and the current time series data and voltage time series data are predicted to generate the SOH value of the backup battery and a backup battery replacement suggestion based on the SOH value, which is then uploaded to the terminal via a wireless module.

[0009] Preferably, the wireless module is one or more of the following: Zigbee module, 4G / 5G, Bluetooth module, and WiFi module.

[0010] Preferably, a switching circuit;

[0011] The control terminal of the switching circuit is electrically connected to the output terminal of the controller, and it can switch the power supply of the emergency lighting lamp body based on the control signal of the controller.

[0012] Preferably, the switching circuit includes a relay;

[0013] The relay coil is electrically connected to the output terminal of the controller. The first set of contacts of the relay is used to connect the emergency lighting body and the backup battery, and the second set of contacts of the relay is used to connect the emergency lighting body and the mains power.

[0014] Preferably, the system further includes an inverter disposed between the backup battery and the emergency lighting unit, wherein the control terminal of the inverter is electrically connected to the output terminal of the controller.

[0015] Preferably, the voltage acquisition unit is a voltage acquisition circuit connected in series between the backup battery and the emergency lighting body, and the current acquisition unit is a current transformer sleeved in the circuit between the backup battery and the emergency lighting body.

[0016] Preferably, the battery health status assessment model is an LSTM model trained based on historically collected battery discharge data, and its training process includes:

[0017] Historical data is input into an LSTM model to process time series data, extract time-related dynamic features, and generate SOH values ​​based on these dynamic features. The mean squared error function is used to calculate the actual SOH values ​​and the generated SOH values, and the weights of the LSTM model are adjusted based on the calculation results. The historical discharge data includes: the voltage change curve during the discharge process, the current change curve during the discharge process, and the corresponding SOH values.

[0018] Preferably, the method further includes: extracting the SOH value change trajectory recorded in multiple tests, fitting it to the LSTM model, using the current SOH value as the initial condition, and predicting the SOH value decrease curve in the future.

[0019] The second embodiment of the present invention provides a detection system for backup batteries of emergency lighting, characterized in that it includes a cloud platform, a terminal, and a detection device for backup batteries of emergency lighting as described above. The controller can upload the collected data and processed data to the cloud platform, and the terminal can access the cloud platform to view the data.

[0020] The present invention provides a detection device and system for backup batteries in emergency lighting. The controller switches the emergency lighting unit from mains power to backup battery power at preset intervals. Simultaneously, by switching the emergency lighting unit from mains power to backup battery power, a pre-built battery health status assessment model is invoked, and the current and voltage time-series data are predicted to generate the SOH value of the backup battery and a backup battery replacement suggestion based on the SOH value. This information is then uploaded to a terminal via a wireless module, solving the inconvenience of manually testing the large number of backup batteries for emergency lighting in factories, shopping malls, or residential buildings. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of a detection device for a backup battery in emergency lighting provided in the first embodiment of the present invention;

[0022] Figure 2 This is a schematic diagram of the execution flow of the controller provided in the second embodiment of the present invention. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] To better understand the technical solution of the present invention, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0025] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0026] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0027] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0028] The terms "first" and "second" used in the embodiments are merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first" and "second" can be interchanged in a specific order or sequence where permissible. It should be understood that the objects distinguished by "first" and "second" can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein.

[0029] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0030] This invention discloses a detection device and system for backup batteries 7 of emergency lighting, which aims to solve the inconvenience of manually testing the large number of backup batteries 7 of emergency lighting in factories, shopping malls or residential buildings.

[0031] Please participate Figure 1 The first embodiment of the present invention provides a detection device for a backup battery 7 of an emergency lighting system, comprising: an adapter disposed between the emergency lighting body 5 and the backup battery 7, wherein the adapter includes a controller 1 disposed therein, a wireless module 4 electrically connected to the radio frequency terminal of the controller 1, a current acquisition unit 2 and a voltage acquisition unit 3 electrically connected to the input terminal of the controller 1;

[0032] It should be noted that the large number of emergency lighting backup batteries 7 in factories, shopping malls or residential buildings should be able to work continuously for 2 hours after the mains power is cut off. If the backup batteries 7 can only work for less than 2 hours, they need to be replaced to avoid the problem of not being able to power the emergency lighting equipment in the event of an emergency.

[0033] In this embodiment, the core of the adapter is a controller 1, which acts as the main processing unit, responsible for coordinating the operation of the adapter's various modules and communication with external devices. The radio frequency terminal of controller 1 is directly electrically connected to the wireless module 4, enabling real-time data transmission with the cloud platform or other devices. This ensures that test data and control signals can be transmitted efficiently and reliably between the device and the cloud platform.

[0034] Furthermore, the voltage acquisition unit 3 employs a series voltage acquisition circuit, directly connected between the backup battery 7 and the emergency lighting lamp body 5. It can monitor the voltage changes of the backup battery 7 supplying power to the lamp body in real time, ensuring high accuracy of the acquired voltage data without affecting the normal power supply to the lamp body. The current acquisition unit 2 uses a current transformer, which is installed in the circuit loop between the backup battery 7 and the emergency lighting lamp body 5. The current transformer obtains the magnitude of the current in the loop through the principle of induction, without direct contact with the circuit. This not only improves the safety of current acquisition but also avoids any physical alteration to the wiring of the lamp body and the backup battery 7. In actual operation, these acquisition units transmit the acquired voltage and current signals to the controller 1 inside the adapter, where the controller 1 processes and analyzes the data.

[0035] Furthermore, the design of the wireless module 4 in the adapter offers flexibility, allowing for one or more of the following: a Zigbee module, a 4G / 5G module, a Bluetooth module, or a WiFi module. The specific module or combination used depends on the application scenario's requirements for data transmission distance, speed, and power consumption. For example, a Zigbee module is preferred in environments requiring low power consumption and short-range transmission; a 4G / 5G module is more suitable for scenarios requiring wide-area coverage and high-speed transmission; a Bluetooth module is suitable for short-range point-to-point communication, such as direct interaction between portable devices and lighting fixtures; and a WiFi module provides high-speed data transmission capabilities, suitable for real-time monitoring and data uploading in a local area network environment.

[0036] Furthermore, the switching circuit 8 is used to switch the power supply of the emergency lighting unit 5 between mains power and backup battery 7, so as to ensure that the emergency lighting unit 5 can automatically switch to emergency mode powered by backup battery 7 when the mains power fails or malfunctions. The control terminal of the switching circuit 8 is electrically connected to the output terminal of the controller 1, and the controller 1 triggers the switching circuit 8 to perform the power supply switching operation by sending a control signal.

[0037] Specifically, the switching circuit 8 contains a relay, whose coil is electrically connected to the output of the controller 1. The first set of contacts of the relay is connected to the backup battery 7 and the emergency lighting unit 5. When the controller 1 issues a switching command, the relay closes the first set of contacts, allowing the emergency lighting unit 5 to draw power from the backup battery 7. Under normal mains power supply conditions, the relay remains in its default state, and the second set of contacts connects the mains power and the emergency lighting unit 5, ensuring that the lighting unit is powered by the mains power.

[0038] When the mains power fails or the controller 1 detects that it needs to switch to emergency mode, the controller 1 sends a control signal to the relay, the relay coil is energized and the first set of contacts closes, switching to the backup battery 7 power supply state.

[0039] Furthermore, an inverter 6 is installed between the backup battery 7 and the emergency lighting unit 5 to convert the DC power supplied by the backup battery 7 into AC power suitable for the emergency lighting unit 5. The control terminal of the inverter 6 is electrically connected to the output terminal of the controller 1, and its operating status is managed by control signals issued by the controller 1. When the mains power is normally supplied, the emergency lighting unit 5 usually operates directly through the mains power, and the inverter 6 is in standby mode and does not participate in power transmission. However, when the mains power fails or an emergency test is required, the controller 1 detects the change in power supply status and activates the inverter 6 by sending a start signal to the control terminal of the inverter 6. The inverter 6 then starts working, converting the DC power from the backup battery 7 into AC power and stably supplying it to the emergency lighting unit 5 to ensure that the lighting system can still operate normally during mains power outages.

[0040] Please see Figure 2 The controller 1 is configured to execute a computer program stored therein to perform the following steps:

[0041] S101, at preset intervals, the emergency lighting lamp body 5 is switched from mains power to backup battery 7 power supply, and the backup battery 7 discharge data collected by current acquisition unit 2 and voltage acquisition unit 3 is acquired, wherein the discharge data includes current timing data and voltage timing data;

[0042] It should be noted that, through the set control logic, the power supply of the emergency lighting unit 5 is automatically switched from mains power to backup battery 7 at preset time intervals (e.g., weekly or monthly) to conduct battery discharge tests. This switching operation is controlled by controller 1, which activates the switching circuit 8 by outputting a control signal, disconnecting the emergency lighting unit 5 from mains power and switching it to backup battery 7 power supply. After the switch is completed, backup battery 7 begins to provide power to emergency lighting unit 5, simulating the actual operating state under emergency power outage conditions. During this process, current acquisition unit 2 and voltage acquisition unit 3 monitor the discharge status of backup battery 7 in real time, collecting current timing data and voltage timing data during the battery discharge process, respectively. These data are dynamic parameters recorded in chronological order, which can fully reflect the changes in current and voltage of the battery during discharge. For example, current acquisition unit 2 senses the real-time value of the discharge current through a current transformer set in the circuit, while voltage acquisition unit 3 measures the dynamic changes in battery output voltage through a voltage acquisition circuit connected in series between backup battery 7 and the lighting unit.

[0043] S102, the pre-built battery health status assessment model is invoked, and the current time series data and voltage time series data are predicted to generate the SOH value of the backup battery 7 and the replacement suggestion of the backup battery 7 based on the SOH value, and then uploaded to the terminal through the wireless module 4.

[0044] After completing the discharge test of backup battery 7 and acquiring complete current and voltage time-series data, the controller 1 invokes a pre-built battery health status assessment model to process and analyze this data. This model, developed based on historical training data, can correlate the dynamic characteristics of backup battery 7 during discharge with its State of Health (SOH) to assess the battery's current health level. Specifically, after the system inputs the current and voltage time-series data into the assessment model, the model first extracts features from this data to identify key parameters reflecting battery performance, such as voltage decay rate, current fluctuation amplitude, and power change trends during discharge. These parameters are then input into the model's core calculation logic and compared with preset health assessment indicators (such as nominal capacity and nominal discharge efficiency) to calculate the battery's current SOH value. The SOH value is usually expressed as a percentage, reflecting the proportion of the battery's actual performance retained relative to that of a brand-new battery. For example, an SOH value of 85% indicates that the battery's current energy storage and release capacity is 85% of its capacity in its brand-new state.

[0045] Once the State of Health (SOH) value is calculated, the system generates a battery replacement recommendation based on preset replacement conditions. For example, if the SOH value is below a set warning threshold (e.g., 60%), the system generates a maintenance reminder to "recommend battery replacement"; if the SOH value is within a safe range, it generates a message stating "Battery status is normal, no replacement required." To enable real-time monitoring and remote management, these calculation results, including the SOH value and replacement recommendations, are uploaded to the user terminal or cloud management platform via the wireless module 4 inside controller 1. Users can view the battery health status report through a mobile application or the backend system and schedule maintenance operations based on the replacement recommendations.

[0046] In one possible embodiment of the present invention, the battery health status assessment model is constructed using a Long Short-Term Memory (LSTM) neural network. This network leverages the battery's ability to process time-series data to analyze battery discharge data and generate a State of Health (SOH) value reflecting the battery's current health status. The model is trained based on historically collected battery discharge data, including curves showing voltage changes over time, current changes over time, and the SOH value corresponding to each discharge. This data is used to establish the correlation between input features and the target output.

[0047] At the start of the training process, historical data is input into the LSTM model. The model, through its unique structure, captures the dynamic characteristics of the time-series data, including the trends and fluctuations of voltage and current over time during discharge, and their potential relationship with battery health. The LSTM unit, through a memory and forgetting mechanism, focuses on the voltage and current changes at key moments during discharge, while ignoring noise information unrelated to battery health.

[0048] After extracting time-related dynamic features, these features are mapped to the target output SOH value, generating the model's predicted value. Subsequently, the predicted SOH value is compared with the corresponding true SOH value, and the difference between the two is calculated. The error is calculated based on the mean squared error (MSE) loss function, which amplifies large deviations through squared errors, ensuring the model can more accurately fit the SOH value. To optimize model performance, the training process uses the error values ​​to backpropagate and adjust the weights of the LSTM model, reducing the error values ​​through multiple iterations and gradually improving the model's predictive ability.

[0049] Based on the training process described above, the LSTM model can accurately capture time-series patterns in discharge data, identify the health characteristics of the battery under different usage conditions, and thus infer the current state of equilibrium (SOH) value from newly acquired discharge data, supporting further health assessment and lifespan prediction. The model's training enables it to adapt to various battery types and discharge environments, providing intelligent support for battery state assessment.

[0050] In one possible implementation of the present invention, the method further includes: extracting the SOH value change trajectory recorded in multiple tests, fitting it to the LSTM model, using the current SOH value as the initial condition, and predicting the SOH value decrease curve in the future time period.

[0051] It should be noted that the SOH values ​​recorded from multiple tests are stored in time series format. This data reflects the degradation pattern of the battery during long-term use, including the gradual decrease in SOH value over time, as well as possible nonlinear characteristics or phased degradation patterns. Based on its ability to process time series data, the LSTM model can learn the dynamic changes in these historical trajectories and build a model that can predict future changes in SOH value.

[0052] In practical applications, the current State of Health (SOH) value serves as the initial input to the LSTM model. Combined with previously learned SOH value change patterns, the model begins to predict the future trend of the battery's SOH value. The LSTM's memory cells dynamically combine the initial SOH value with historical trajectory features stored in the model to generate a predicted SOH value decline curve. This curve not only reflects the overall trend of SOH value decay over time but also captures key nodes in the degradation process, such as stages where the health status suddenly accelerates. In this way, the model can accurately predict the battery's remaining lifespan and future health status, providing users with precise battery replacement time recommendations.

[0053] The second embodiment of the present invention provides a detection system for backup batteries of emergency lighting, characterized in that it includes a cloud platform, a terminal, and a detection device for backup batteries of emergency lighting as described above. The controller can upload the collected data and processed data to the cloud platform, and the terminal can access the cloud platform to view the data.

[0054] The present invention provides a detection device and system for backup batteries in emergency lighting. The controller switches the emergency lighting unit from mains power to backup battery power at preset intervals. Simultaneously, by switching the emergency lighting unit from mains power to backup battery power, a pre-built battery health status assessment model is invoked, and the current and voltage time-series data are predicted to generate the SOH value of the backup battery and a backup battery replacement suggestion based on the SOH value. This information is then uploaded to a terminal via a wireless module, solving the inconvenience of manually testing the large number of backup batteries for emergency lighting in factories, shopping malls, or residential buildings.

[0055] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A detection device for backup batteries in emergency lighting, characterized in that, include: An adapter is configured between the emergency lighting body and the backup battery, wherein the adapter includes a controller configured therein, a wireless module electrically connected to the radio frequency terminal of the controller, and a current acquisition unit and a voltage acquisition unit electrically connected to the input terminal of the controller; The controller is configured to execute a computer program stored therein to perform the following steps: At preset intervals, the emergency lighting unit is switched from mains power to backup battery power, and backup battery discharge data collected by current acquisition unit and voltage acquisition unit is acquired, wherein the discharge data includes current timing data and voltage timing data; A pre-built battery health status assessment model is invoked, and the current time series data and voltage time series data are predicted to generate the SOH value of the backup battery and a backup battery replacement suggestion based on the SOH value, which is then uploaded to the terminal via a wireless module.

2. The detection device for backup batteries in emergency lighting according to claim 1, characterized in that, The wireless module is one or more of the following: Zigbee module, 4G / 5G, Bluetooth module, and WiFi module.

3. The detection device for backup batteries in emergency lighting according to claim 1, characterized in that, Switching circuit; The control terminal of the switching circuit is electrically connected to the output terminal of the controller, and it can switch the power supply of the emergency lighting lamp body based on the control signal of the controller.

4. The detection device for backup batteries in emergency lighting according to claim 3, characterized in that, The switching circuit includes a relay; The relay coil is electrically connected to the output terminal of the controller. The first set of contacts of the relay is used to connect the emergency lighting body and the backup battery, and the second set of contacts of the relay is used to connect the emergency lighting body and the mains power.

5. The detection device for a backup battery in emergency lighting according to claim 4, characterized in that, It also includes an inverter configured between the backup battery and the emergency lighting unit, wherein the control terminal of the inverter is electrically connected to the output terminal of the controller.

6. The detection device for a backup battery in emergency lighting according to claim 4, characterized in that, The voltage acquisition unit is a voltage acquisition circuit connected in series between the backup battery and the emergency lighting body, and the current acquisition unit is a current transformer installed in the circuit between the backup battery and the emergency lighting body.

7. The detection device for backup batteries in emergency lighting according to claim 1, characterized in that, The battery health status assessment model is an LSTM model trained based on historically collected battery discharge data. Its training process includes: Historical data is input into an LSTM model to process time series data, extract time-related dynamic features, and generate SOH values ​​based on these dynamic features. The mean squared error function is used to calculate the actual SOH values ​​and the generated SOH values, and the weights of the LSTM model are adjusted based on the calculation results. The historical discharge data includes: the voltage change curve during the discharge process, the current change curve during the discharge process, and the corresponding SOH values.

8. The detection device for a backup battery in emergency lighting according to claim 7, characterized in that, Also includes: The trajectory of SOH value changes recorded in multiple tests is extracted and fitted to the LSTM model. The current SOH value is used as the initial condition to predict the decline curve of SOH value in the future.

9. A detection system for backup batteries in emergency lighting, characterized in that, The device includes a cloud platform, a terminal, and a detection device for a backup battery for emergency lighting as described in any one of claims 1 to 8. The controller is capable of uploading the collected and processed data to the cloud platform, and the terminal is capable of accessing the cloud platform to view the data.

Images