A Charging and Discharging Detection Method, Device, Equipment and Medium for Mine-used Lithium Batteries

Abstract

The present invention belongs to the technical field of battery detection, and specifically provides a charge and discharge detection method for mine-used lithium batteries, including the steps of: collecting mine environment parameters and lithium battery state parameters in real time; obtaining historical construction logs, and according to the mine environment parameters, calculating the corresponding construction stage of the mine environment parameters based on the historical construction logs through time series analysis; inputting the mine environment parameters and the corresponding construction stage into a trained environment risk assessment model to output the current environment risk level; dynamically adjusting the battery detection frequency and charge and discharge protection thresholds according to the lithium battery state parameters and the current environment risk level and generating a control instruction containing the adjusted parameters; sending the control instruction to the battery management system based on switching the communication protocol according to the environment risk level; by calculating the environment risk level, corresponding measures can be taken according to the risk level; and by adding the environment risk level as a switching condition, the communication reliability and stability in different environments are ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of battery detection, and particularly relates to a charge and discharge detection method, device, equipment and medium for mine lithium batteries. Background Art

[0002] With the acceleration of the intelligent and electrified process of mine exploitation, mine explosion-proof lithium batteries have been widely used in the power supply systems of underground electric equipment (such as mine trucks and drilling equipment) due to their advantages of high energy density and long cycle life. However, the mine environment has extreme working condition characteristics such as high gas concentration, high dust density, and strong vibration, which pose a severe challenge to the safety management of lithium batteries. In the existing technologies, there are some defects, for example:

[0003] Single environmental parameter monitoring: Most solutions only focus on battery body parameters (such as voltage and temperature), while ignoring the unique environmental factors in mines, such as gas concentration and dust density, resulting in incomplete risk assessment.

[0004] Static threshold setting: Traditional methods use fixed charge and discharge thresholds (such as charging voltage ≤ 4.2V), which cannot be dynamically adjusted according to the environmental risk level. For example, in a high-risk scenario where the gas concentration > 1%, even if the battery parameters are normal, the charge and discharge power still needs to be significantly reduced to prevent electric sparks, and the existing technologies lack such flexible control mechanisms.

[0005] Insufficient communication reliability: Most existing solutions use a single communication protocol (such as CAN bus). Due to problems such as electromagnetic interference, signal attenuation, and equipment occlusion in mine tunnels, the single communication protocol is prone to data loss or data delay when the environment deteriorates, resulting in response lag and inability to trigger the protection mechanism in a timely manner.

[0006] In view of the above problems, there is an urgent need for a charge and discharge detection method that can integrate multiple environmental parameters, dynamically adjust the detection strategy, and adaptively optimize the communication link to achieve the full-life-cycle safety control of lithium batteries in a complex mine environment. Summary of the Invention

[0007] In order to overcome the deficiencies of the prior art, the present invention provides a charge and discharge detection method, device, equipment and medium for mine lithium batteries to solve the problems in the prior art.

[0008] One embodiment of the present invention provides a charge and discharge detection method for mine lithium batteries, including the following steps:

[0009] Real-time collect mine environmental parameters and lithium battery state parameters, where the mine environmental parameters at least include gas concentration, dust density, and vibration frequency, and the lithium battery state parameters at least include voltage, current, and temperature;

[0010] Obtain historical construction logs. Based on the collected mine environmental parameters, calculate the corresponding construction stages of the mine environmental parameters through time series analysis based on the historical construction logs;

[0011] Input the mine environmental parameters and the corresponding construction stages into the trained environmental risk assessment model, and output the current environmental risk level through the environmental risk assessment model;

[0012] According to the lithium battery state parameters and the current environmental risk level, dynamically adjust the battery detection frequency and the charge and discharge protection threshold, and generate a control instruction containing the adjusted parameters;

[0013] Switch the communication protocol based on the environmental risk level, and send the control instruction to the battery management system using the switched communication protocol;

[0014] Among them, in the step of dynamically adjusting the battery detection frequency and the charge and discharge protection threshold according to the lithium battery state parameters and the current environmental risk level and generating a control instruction containing the adjusted parameters, the dynamic adjustment includes:

[0015] When the environmental risk level increases, increase the detection frequency and decrease the upper limit of the charge and discharge current;

[0016] When the environmental risk level decreases, decrease the detection frequency and increase the upper limit of the charge and discharge current.

[0017] By adopting the above solution, mine environmental parameters are collected and historical construction logs are obtained. The collected mine environmental parameters and the obtained historical construction logs are input into the environmental risk assessment model to obtain the risk level of the current environment in the mine, and corresponding measures can be taken according to the current risk level; the historical construction logs are the construction arrangements, completed projects, construction time arrangements, etc. in the mine. By using time series analysis, the current construction stage corresponding to the collected mine environmental parameters can be calculated based on the historical construction logs. By inputting the mine environmental parameters and the obtained corresponding construction stage into the trained environmental risk assessment model, the credibility of the output current environmental risk level can be increased. The state parameters of the lithium battery are collected. According to the collected state parameters of the lithium battery and the obtained current risk level, the detection frequency and the dynamic adjustment of the charge and discharge protection threshold of the explosion-proof lithium battery for mines can be made accordingly to adapt to the current risk level. For example, when it is found that the current risk level increases, the detection frequency is increased and the charge and discharge current is reduced. If an abnormality occurs, the detection frequency is increased to detect the abnormality faster. At the same time, the current is reduced to prevent the battery from overloading and causing danger in a high-risk environment. When it is found that the risk level decreases, recovery is carried out; through dynamic adjustment, rapid response is achieved at high risk and gradual recovery is carried out after the risk decreases, thus avoiding the burden on the equipment caused by frequent switching. At the same time, the corresponding communication protocol is determined and switched according to the current risk level. For example, when the risk level is low, CAN bus communication can be used to ensure the real-time transmission of control instructions. When the risk level is high, in order to avoid problems such as signal attenuation, decreased stability, and even signal interruption caused by the deterioration of the mine internal environment, such as an increase in gas concentration, an increase in dust density, or an increase in vibration frequency, and the failure to trigger the protection mechanism in time, resulting in danger, the communication protocol is automatically switched to LoRa spread spectrum communication and data compression is enabled to ensure the stability of the transmission of control instructions. By adding the environmental risk level as a switching condition, the reliability and stability of communication in different environments are ensured, especially in the complex mine environment, achieving the effect of adaptive switching.

[0018] In one embodiment, after the step of switching the communication protocol based on the environmental risk level and sending the control instruction to the battery management system by using the switched communication protocol, the following steps are further included:

[0019] The battery management system receives the control instruction and adjusts the output parameters according to the control instruction;

[0020] Among them, adjusting the output parameters according to the control instruction specifically includes:

[0021] When the real-time current in the collected lithium battery state parameters is within the upper threshold range of the charge and discharge current corresponding to the current environmental risk level, and the real-time voltage is within the safety threshold range, the output parameters of the battery management system only include the adjustment of the detection frequency;

[0022] When the real-time current in the collected lithium battery state parameters is greater than the upper threshold of the charge and discharge current corresponding to the current environmental risk level, and the real-time voltage is within the safety threshold range, the output parameters of the battery management system include the adjustment of the detection frequency and the adjustment of the current.

[0023] By adopting the above scheme, the safety values of the upper limits of the charge and discharge currents corresponding to different environmental risk levels are set, and the adjustment of the lithium battery is determined according to the current and voltage values of the collected lithium battery state parameters, so that the charge and discharge of the lithium battery can be adjusted under different environmental risk levels, and the current voltage value is considered during the adjustment to prevent damage to the explosion-proof lithium battery caused by overvoltage or undervoltage and the occurrence of safety accidents.

[0024] In one embodiment, in the step of inputting the mine environmental parameters and the corresponding construction stage into the trained environmental risk assessment model and outputting the current environmental risk level through the environmental risk assessment model, the construction and training of the environmental risk assessment model include the following steps:

[0025] Collect the historical mine environmental parameters, their corresponding historical accident data, and obtain the historical construction logs for preprocessing to obtain standardized feature data applied to the machine model as input data;

[0026] Use the learning algorithm to train the environmental risk assessment model with the standardized feature data obtained after preprocessing to obtain the trained environmental risk assessment model, which is used to receive the mine environmental parameters and the corresponding construction stage in real time and output the current risk level.

[0027] By adopting the above scheme, the collected historical mine environmental parameters, their corresponding historical accident data, and the obtained historical construction logs are preprocessed to make the data meet the input requirements of the machine learning model; the preprocessed data is used to train the environmental risk assessment model with the learning algorithm, so that the obtained environmental risk assessment model can output the corresponding risk assessment results according to the input data in the future.

[0028] In one embodiment, in the step of collecting the historical mine environmental parameters, their corresponding historical accident data, and obtaining the historical construction logs for preprocessing to obtain standardized feature data applied to the machine model as input data, the specific steps include the following:

[0029] Collect historical mine environmental parameters and their corresponding historical accident data, and label a risk level for each historical environmental parameter according to the type and severity of the historical accident data. The risk levels include Level L1 to Level L4;

[0030] Perform normalization processing on the labeled historical environmental parameters and historical construction logs to obtain standardized feature data. The standardized feature data includes at least historical gas concentration, historical dust density, historical vibration frequency, and historical construction logs.

[0031] By adopting the above solution, risk level labels are assigned to the collected historical mine environmental parameters and their corresponding historical accident data, enabling subsequent output of real-time environmental risk levels based on real-time environmental parameters. Normalization processing is performed on the labeled data and historical construction logs to obtain standardized feature data, making the data suitable for the input requirements of machine learning models.

[0032] In one embodiment, the step of using the learning algorithm to train the environmental risk assessment model with the standardized feature data obtained after preprocessing to obtain a trained environmental risk assessment model, and using the trained environmental risk assessment model to receive real-time mine environmental parameters and corresponding construction stages and output the current risk level specifically includes the following steps:

[0033] Divide the standardized feature data into a training set and a test set;

[0034] Use the standardized feature data in the training set, with gas concentration, dust density, vibration frequency, and construction logs as input features, and use the random forest algorithm to train the environmental risk assessment model to obtain a trained environmental risk assessment model and output risk levels of L1 to L4;

[0035] Use the test set to verify the performance of the environmental risk assessment model, require that the recall rate of Level L4 risk is not lower than a preset threshold, and optimize the parameters of the environmental risk assessment model according to the verification results;

[0036] Based on the optimized environmental risk assessment model, it is used to receive real-time mine environmental parameters and corresponding construction stages and output risk levels.

[0037] By adopting the above solution, the standardized feature data is divided into a training set and a test set. The training set is used to train the machine learning model to obtain a trained model and output the corresponding risk levels. The test set is used to verify the performance of the trained model, and the model is optimized according to the verification results, improving the performance and accuracy of the model; the trained and optimized model is used to receive real-time mine environmental parameters and output risk levels, so that corresponding measures can be taken according to the output risk levels.

[0038] In one embodiment, in the step of dynamically adjusting the battery detection frequency and the charge and discharge protection threshold according to the lithium battery state parameters and the current environmental risk level and generating a control instruction including the adjustment parameters, the dynamic adjustment further includes:

[0039] When the temperature in the lithium battery state parameters exceeds a first preset threshold, forcibly increase the detection frequency and decrease the upper limit of the charge and discharge current;

[0040] When the temperature exceeds a second preset threshold, trigger a charge and discharge circuit cut-off instruction.

[0041] By adopting the above solution, taking the temperature as an independent parameter, triggering the protection action prior to the environmental risk level, so as to ensure rapid response under extreme working conditions. Real-time monitor the temperature value in the lithium battery state parameters, adjust the current environmental risk level according to the temperature value. When it is detected that the temperature exceeds the first preset threshold, regardless of the mine environmental parameters and the current environmental risk level, directly generate a control instruction to forcibly increase the detection frequency and decrease the upper limit of the charge and discharge current to the battery management system for early warning; when it is detected that the temperature exceeds the second preset threshold, forcibly cut off the charge and discharge circuit to prevent accidents.

[0042] In one embodiment, the collected lithium battery state parameters further include the battery health state. In the step of dynamically adjusting the battery detection frequency and the charge and discharge protection threshold according to the lithium battery state parameters and the current environmental risk level and generating a control instruction including the adjustment parameters, the dynamic adjustment further includes:

[0043] Based on the available value of the current battery health state, if the available value is within the preset threshold range, and when the environmental risk level increases, increase the detection frequency and decrease the upper limit of the charge and discharge current based on the loss value of the battery health state;

[0044] If the available value of the current battery health state is less than the preset threshold, trigger a charge and discharge circuit cut-off instruction.

[0045] By adopting the above solution, the collected lithium battery state parameters further include the battery health state. When dynamically adjusting the charge and discharge detection parameters of the lithium battery, consider the current health state of the battery. If the loss value of the battery health state reaches a certain value, cut off the charge and discharge circuit to prevent accidents; if the available value of the battery health state is still within the preset threshold range, when decreasing the upper limit of the charge and discharge current, add the loss value of the battery health state to calculate, avoiding that when normally decreasing the upper limit of the charge and discharge current, due to a certain loss of the battery health state, it may still conduct at a higher current after decreasing the upper limit of the charge and discharge current.

[0046] This application further relates to a charge and discharge detection device for a mine-used lithium battery, including:

[0047] A data acquisition module, configured to acquire mine environment parameters and lithium battery state parameters in real time. The mine environment parameters at least include gas concentration, dust density and vibration frequency, and the lithium battery state parameters at least include voltage, current and temperature;

[0048] An analysis module, configured to obtain historical construction logs, and calculate the corresponding construction stages of the mine environment parameters based on the historical construction logs through time series analysis according to the acquired mine environment parameters;

[0049] A risk assessment module, configured to input the mine environment parameters and the corresponding construction stages into a trained environment risk assessment model, and output the current environment risk level through the environment risk assessment model;

[0050] A dynamic adjustment module, configured to dynamically adjust the battery detection frequency and the charge and discharge protection threshold according to the lithium battery state parameters and the current environment risk level, and generate a control instruction including the adjustment parameters;

[0051] A communication switching module, configured to switch the communication protocol based on the environment risk level, and send the control instruction to the battery management system by using the switched communication protocol.

[0052] By adopting the above scheme, mine environmental parameters are collected and historical construction logs are obtained. The collected mine environmental parameters and the obtained historical construction logs are input into the environmental risk assessment model to obtain the risk level of the current environment in the mine, and corresponding measures can be taken according to the current risk level; the historical construction logs are the construction arrangements, completed projects, construction time arrangements, etc. in the mine. By using time series analysis, the current construction stage corresponding to the collected mine environmental parameters can be calculated based on the historical construction logs. By inputting the mine environmental parameters and the obtained corresponding construction stage into the trained environmental risk assessment model, the credibility of the output current environmental risk level can be increased. The state parameters of the lithium battery are collected. According to the collected state parameters of the lithium battery and the obtained current risk level, the detection frequency and the dynamic adjustment of the charge and discharge protection threshold of the mine explosion-proof lithium battery can be made accordingly to adapt to the current risk level. For example, when it is found that the current risk level increases, the detection frequency is increased and the charge and discharge current is reduced. If an abnormality occurs, the detection frequency is increased to detect the abnormality faster. At the same time, the current is reduced to prevent the battery from overloading and causing danger in a high-risk environment. When it is found that the risk level decreases, recovery is carried out; through dynamic adjustment, a quick response is made in high-risk situations and gradual recovery is carried out after the risk decreases, thus avoiding the burden on the equipment caused by frequent switching. At the same time, the corresponding communication protocol is determined and switched according to the current risk level. For example, when the risk level is relatively low, CAN bus communication can be used to ensure the real-time transmission of control instructions. When the risk level is relatively high, in order to avoid problems such as signal attenuation, decreased stability or signal interruption caused by the deterioration of the mine internal environment, such as an increase in gas concentration, an increase in dust density or an increase in vibration frequency, and the inability to trigger the protection mechanism in time, resulting in danger, the communication protocol is automatically switched to LoRa spread spectrum communication and data compression is enabled to ensure the stability of the control instruction transmission. By adding the environmental risk level as the switching condition, the reliability and stability of communication in different environments are ensured, especially in the complex mine environment, achieving the effect of adaptive switching.

[0053] This application also relates to a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above method for detecting the charge and discharge of a mine explosion-proof lithium battery are implemented.

[0054] This application also relates to a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the above method for detecting the charge and discharge of a mine explosion-proof lithium battery are implemented.

[0055] The method, device, equipment and medium for detecting the charge and discharge of a mine explosion-proof lithium battery provided by the above embodiments have the following beneficial effects:

[0056] By collecting mine environmental parameters and obtaining historical construction logs, input the collected mine environmental parameters and the obtained historical construction logs into the environmental risk assessment model to obtain the risk level of the current environment in the mine, and corresponding measures can be taken according to the current risk level; the historical construction logs are the construction arrangements, completed projects, construction time arrangements, etc. in the mine. By using time series analysis, the current construction stage corresponding to the collected mine environmental parameters can be calculated based on the historical construction logs. By inputting the mine environmental parameters and the obtained corresponding construction stage into the trained environmental risk assessment model, the credibility of the output current environmental risk level can be increased. Collect the state parameters of the lithium battery. According to the collected state parameters of the lithium battery and the obtained current risk level, the detection frequency and the dynamic adjustment of the charge and discharge protection threshold of the explosion-proof lithium battery for mines can be made accordingly to adapt to the current risk level. For example, when it is found that the current risk level increases, increase the detection frequency and reduce the charge and discharge current. If an abnormality occurs, increase the detection frequency to detect the abnormality faster. At the same time, reduce the current to prevent the battery from overloading and causing danger in a high-risk environment. When it is found that the risk level decreases, then recover; through dynamic adjustment, it can quickly respond in high-risk situations and gradually recover after the risk decreases, thus avoiding the burden on the equipment caused by frequent switching. At the same time, determine and switch the corresponding communication protocol according to the current risk level. For example, when the risk level is relatively low, CAN bus communication can be used to ensure the real-time transmission of control instructions. When the risk level is relatively high, in order to avoid problems such as signal attenuation, decreased stability, and even signal interruption caused by the deterioration of the mine internal environment, such as an increase in gas concentration, an increase in dust density, or an increase in vibration frequency, and thus being unable to trigger the protection mechanism in time and causing danger, the communication protocol is automatically switched to LoRa spread spectrum communication and data compression is enabled to ensure the stability of the control instruction transmission. By adding the environmental risk level as a switching condition, the reliability and stability of communication in different environments are ensured, especially in the complex mine environment, achieving the effect of adaptive switching. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on the structures shown in these drawings without creative efforts.

[0058] Figure 1 It is a flowchart of a method for detecting the charge and discharge of an explosion-proof lithium battery for mines provided by an embodiment of the present invention;

[0059] Figure 2A schematic block diagram of a computer device provided by an embodiment of the present invention. Detailed implementation manners

[0060] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0061] It should be noted that if there are directional indications (such as up, down, left, right, front, back,...) involved in the embodiments of the present invention, the directional indications are only used to explain the relative positional relationship and movement conditions between components in a specific posture. If the specific posture changes, the directional indications will also change accordingly.

[0062] In addition, if there are descriptions such as "first" and "second" involved in the embodiments of the present invention, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, if "and / or" or "and / or" appears throughout the text, its meaning includes three parallel scenarios. Taking "A and / or B" as an example, it includes scenario A, or scenario B, or the scenario where A and B are satisfied simultaneously. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the fact that those of ordinary skill in the art can implement it. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the protection scope required by the present invention.

[0063] Referring to Figure 1 , one embodiment of the present invention provides a method for detecting the charging and discharging of a mining lithium battery, including the following steps:

[0064] S10. Real-time collect mine environmental parameters and lithium battery state parameters, where the mine environmental parameters at least include gas concentration, dust density, and vibration frequency, and the lithium battery state parameters at least include voltage, current, and temperature.

[0065] As described in step S10 above, the mine environmental parameters collected in this embodiment at least include gas concentration, dust density, and vibration frequency, and the state parameters of the lithium battery collected at least include voltage, current, and temperature. For the collection of gas concentration, it can be monitored and collected in real time through an infrared gas sensor, with a measurement range of 0~5% CH4, an accuracy of ±0.1%, and a sampling frequency of 1H; for the collection of dust density, it can be monitored and collected in real time through a laser scattering dust sensor, with a measurement range of 0~100mg / m³, a resolution of 0.1mg / m³, and the data is transmitted through the RS485 interface; for the collection of vibration frequency, it can be monitored and collected in real time by installing a three-axis acceleration sensor on the outer shell of the explosion-proof lithium battery pack, with a monitored vibration frequency spectrum range of 0~2000Hz and a dynamic response time ≤5ms; for the collection of voltage and current, it can be monitored and collected in real time through a Hall voltage sensor and a closed-loop current sensor, with a sampling frequency of 10kHz and an accuracy of ±0.5%; for the collection of temperature, it can be monitored and collected in real time by arranging NTC thermistors on the surface and inside of the explosion-proof lithium battery module, with a temperature measurement range of -40°C~125°C and an error of ±0.5°C. The collected mine environmental parameters and lithium battery state parameters are subjected to data fusion and data preprocessing. For example, the STM32F407 microcontroller is used to align the timestamps of multi-source data, and the sliding window filtering (window length 10s) is used to eliminate noise, and the data is packaged and uploaded to the edge computing gateway device through the CAN bus.

[0066] S20. Obtain the historical construction logs, and based on the collected mine environmental parameters, calculate the corresponding construction stages of the mine environmental parameters through time series analysis based on the historical construction logs.

[0067] As described in step S20 above, the historical construction log includes the construction arrangements in the mine (such as the construction process and stage arrangements of the entire mine), the completed construction projects (such as which step and stage of construction have been completed according to the progress of the construction arrangement), and the construction time arrangements (such as what type of construction is carried out in which time period / morning / afternoon), etc. According to the real-time time of the collected mine environmental parameters and the historical construction log, time series analysis is used to calculate which construction stage in the historical construction log the currently collected mine environmental parameters correspond to, so as to obtain the currently corresponding construction stage. Due to different construction situations, the corresponding mine environmental parameters will be different. For example, in a certain construction stage arrangement, when mechanical cutting, drilling and other operations are carried out, the dust concentration will be relatively high, and when excavation, deep mining, and mechanical equipment operation are carried out, the vibration frequency will be relatively large, etc. Therefore, according to the historical construction log, by using time series analysis, the currently corresponding construction stage corresponding to the collected mine environmental parameters can be calculated based on the historical construction log, that is, it is possible to know the possible changes in the mine environmental parameters corresponding to the currently corresponding construction stage. By inputting the mine environmental parameters and the obtained corresponding construction stage into the trained environmental risk assessment model, the credibility of the currently output environmental risk level by the subsequent environmental risk assessment model can be increased.

[0068] S30. Input the mine environmental parameters and the corresponding construction stage into the trained environmental risk assessment model, and output the current environmental risk level through the environmental risk assessment model.

[0069] As described in step S30 above, the environmental risk assessment model is a pre-trained machine learning model deployed in the edge computing gateway device in the mine, and is used to calculate the risk level of the current environment in the mine. By taking the collected mine environmental parameters (gas concentration, dust density and vibration frequency) and the corresponding construction stage as inputs, the current environmental situation in the mine can be accurately obtained, and according to the preset risk level, the risk level of the current environment can be output, so as to take corresponding measures according to the current risk level to prevent accidents. For example, the preset risk levels are L1 - L4. When the gas concentration ≥ 2% and / or the dust density ≥ 50mg / m³ and / or the vibration frequency ≥ 1500Hz, the environmental risk assessment model outputs level L4 (extremely high risk); if the gas concentration < 0.5%, the dust density < 10mg / m³ and the vibration frequency < 500Hz, it outputs level L1 (low risk).

[0070] Among them, the construction and training of the environmental risk assessment model include the following steps:

[0071] S310. Collect the historical mine environmental parameters, their corresponding historical accident data, and obtain the historical construction log for preprocessing to obtain the standardized feature data applied to the machine model as input data. Specifically, it includes the following steps:

[0072] S311. Collect historical mine environmental parameters and their corresponding historical accident data. According to the type and severity of the historical accident data, label a risk level for each piece of historical environmental parameter. The risk levels include Level L1 to Level L4. For example, the corresponding historical accident data includes mine environmental monitoring records (gas concentration, dust density, vibration frequency) in the past year and corresponding accident reports (such as gas explosion, thermal runaway of the battery caused by equipment short circuit, etc.). Then, according to the accident severity and the corresponding environmental parameter thresholds, the data is labeled into 4 risk levels.

[0073] S312. Normalize the labeled historical environmental parameters and historical construction logs to obtain standardized feature data. The standardized feature data includes at least historical gas concentration, historical dust density, historical vibration frequency, and historical construction logs.

[0074] S320. Use the standardized feature data obtained after preprocessing to train an environmental risk assessment model using a learning algorithm to obtain a trained environmental risk assessment model. The trained environmental risk assessment model is used to receive real-time mine environmental parameters and corresponding construction stages and output the current risk level. Specifically, it includes the following steps:

[0075] S321. Divide the standardized feature data into a training set and a test set;

[0076] S322. Use the standardized feature data in the training set, with gas concentration, dust density, vibration frequency, and construction logs as input features, and use the random forest algorithm to train the environmental risk assessment model to obtain a trained environmental risk assessment model and output risk levels from L1 to L4;

[0077] S323. Use the test set to verify the performance of the environmental risk assessment model, requiring that the recall rate of Level L4 risk is not lower than a preset threshold. For example, it is required that the recall rate of Level L4 risk is not lower than 98%, and optimize the parameters of the environmental risk assessment model according to the verification results;

[0078] S324. Based on the optimized environmental risk assessment model, receive real-time mine environmental parameters and corresponding construction stages and output the risk level.

[0079] S40. Dynamically adjust the battery detection frequency and charge and discharge protection thresholds according to the lithium battery state parameters and the current environmental risk level and generate a control instruction containing the adjusted parameters. The dynamic adjustment includes:

[0080] When the environmental risk level increases, increase the detection frequency and lower the upper limit of the charge and discharge current;

[0081] When the environmental risk level decreases, reduce the detection frequency and increase the upper limit of the charge and discharge current.

[0082] As described in step S40 above, according to the collected state parameters of the lithium battery and the obtained current risk level, the detection frequency and the dynamic adjustment of the charge and discharge protection threshold of the mine-explosion-proof lithium battery can be made accordingly to adapt to the current risk level; among them, the battery detection frequency is the number of times of sampling the battery state (current, voltage) per unit time, and the charge and discharge protection threshold is the safety upper limit of the current allowed for charge and discharge. For the dynamic adjustment rule: the detection frequency increases step by step according to the risk level. For example, when the risk level is L1, the detection frequency is 10 s / time; when the risk level is L2, the detection frequency is 5 s / time, and the frequency is doubled; when the risk level is L3, the detection frequency is 2 s / time, and the frequency is increased by 5 times; when the risk level is L4, the detection frequency is 1 s / time, and the frequency is increased by 10 times. The charge and discharge protection threshold decreases linearly according to the risk level. For example, when the risk level is L1, the safety upper limit of the current is 100%; when the risk level is L2, the safety upper limit of the current is 80%; when the risk level is L3, the safety upper limit of the current is 60%; when the risk level is L4, the safety upper limit of the current is 40%.

[0083] Taking a mine-explosion-proof lithium battery device as an example:

[0084] Initial state: The environmental risk level is L1, the detection frequency is 10 s / time, the upper limit of the charge and discharge current is 100 A, the upper limit of the charge and discharge voltage is 54.6 V, and the lower limit is 42.0 V;

[0085] Risk upgrade and generate corresponding control instructions: When it is detected that the gas concentration increases and the risk level rises to L3, generate a control instruction to adjust the battery detection frequency to 2 seconds / time and the upper limit of the charge and discharge current to 60 A.

[0086] S50. Switch the communication protocol based on the environmental risk level, and use the switched communication protocol to send the control instruction to the battery management system.

[0087] As described in step S50 above, since CAN bus communication has advantages such as high reliability, low latency, and high bandwidth, and LoRa spread spectrum communication has advantages such as long-distance wireless transmission, anti-interference, and low power consumption, in the case of a relatively low risk level, CAN bus communication is preset as the communication protocol for risk levels L1 - L2. When the risk level increases, LoRa spread spectrum communication is preset as the communication protocol for risk levels L3 - L4. This embodiment determines which communication protocol to adopt in the current environment based on the current risk level. For example, in the initial state, the environmental risk level is L1, and CAN bus communication is used. When the environmental risk assessment model outputs that the current environmental risk level has risen to L3, the communication protocol is switched from CAN bus communication to LoRa spread spectrum communication, and then the control instruction is sent to the battery management system using LoRa spread spectrum communication. For the switch between the two communication protocols, a dual-mode hot standby mechanism is adopted to ensure seamless switching between communication protocols; usually, communication is through CAN bus, and at the same time, LoRa spread spectrum communication is in a low-power listening state. When it is detected that the CAN bus communication is interrupted or the risk level ≥ L3, LoRa spread spectrum communication + compression is immediately enabled; for the compression algorithm, it is a preset differential coding + Huffman compression to ensure that the switching delay is less than 100 ms. By adding the environmental risk level as a switching condition, the reliability and stability of communication in different environments are ensured, especially in the complex environment of a mine, achieving the effect of adaptive switching.

[0088] As described in steps S10 - S50 above, in this embodiment, taking a lithium-ion loader in a mine as an example, if the gas concentration in the mine suddenly increases to 2%: the environmental risk assessment model quickly determines that the risk level is L4; at this time, the detection frequency of the lithium battery is increased to 1 time / second, and the upper limit of the charge and discharge current is reduced from 100 A to 40 A; the communication protocol is switched to LoRa spread spectrum communication, and the control instruction is successfully sent to the battery management system to achieve emergency load reduction of the equipment and avoid gas explosion caused by electric sparks.

[0089] In one embodiment, after step S50, the following steps are further included:

[0090] S60. The battery management system receives the control instruction and adjusts the output parameters according to the control instruction.

[0091] Among them, adjusting the output parameters according to the control instruction specifically includes:

[0092] If the real-time current in the collected lithium battery state parameters is within the range of the upper limit threshold of the charge and discharge current corresponding to the current environmental risk level, and the real-time voltage is within the safety threshold range, the output parameters of the battery management system only include the adjustment of the detection frequency;

[0093] If the real-time current in the collected lithium battery state parameters is greater than the upper limit threshold of the charge and discharge current corresponding to the current environmental risk level, and the real-time voltage is within the safe threshold range, the output parameters of the battery management system include adjustments to the detection frequency and the current.

[0094] As described in step S60 above, for example, when the risk level is L3, the safety upper limit of the charge and discharge current is adjusted to 60%. If the initial upper limit of the charge and discharge current is 100A, then the adjusted safety upper limit of the charge and discharge current is 60A. Among the collected lithium battery state parameters, when the real-time current ≤ 60A and the voltage is normal, the current state is maintained, and the generated control instructions only include adjustments to the detection frequency; when the real-time current > 60A, such as 70A, and the voltage is normal, the current is limited to 60A, and the generated control instructions include adjustments to the detection frequency and current limiting control.

[0095] Among them, when the real-time charge and discharge voltage exceeds 54.6V or is lower than 42.0V, regardless of the current risk level and whether the real-time charge and discharge current exceeds the safety upper limit, the charge and discharge circuit is directly cut off to prevent damage to the explosion-proof lithium battery due to overvoltage or undervoltage and the occurrence of safety accidents.

[0096] In one embodiment, in step S40, the dynamic adjustment further includes:

[0097] When the temperature in the lithium battery state parameters exceeds the first preset threshold, the detection frequency is forcibly increased and the upper limit of the charge and discharge current is reduced;

[0098] When the temperature exceeds the second preset threshold, a charge and discharge circuit cut-off instruction is triggered.

[0099] In this embodiment, it is assumed that the first preset threshold of the temperature is 50°C and the second preset threshold of the temperature is 65°C; when dynamically adjusting the battery detection frequency and the charge and discharge protection threshold, if the temperature in the collected lithium battery state parameters exceeds 50°C but does not exceed 65°C, even if the environmental risk level is low, the detection frequency of the lithium battery charge and discharge is forcibly increased for early warning, and the upper limit of the charge and discharge current is reduced to prevent continuous high-current operation from causing continuous temperature rise and accidents. If the temperature in the collected lithium battery state parameters exceeds 65°C, a charge and discharge circuit cut-off instruction is directly triggered and sent to the battery management system.

[0100] In one embodiment, the collected lithium battery state parameters further include the battery health state; in step S40, the dynamic adjustment further includes:

[0101] Based on the available value of the current battery health state, if the available value is within the preset threshold range, and when the environmental risk level increases, the detection frequency is increased and the upper limit of the charge and discharge current is reduced based on the loss value of the battery health state;

[0102] If the available value of the current battery health state is less than the preset threshold, a charge and discharge circuit cut-off instruction is triggered.

[0103] In this embodiment, among the battery state parameters collected in step S10, the state of health of the battery (SOH) is also included. The initial available value of the state of health of the battery is 100%. Assume that the preset threshold range of the available value of the state of health of the battery is 50% - 100%. In the dynamic adjustment of step S40, assume that the current environmental risk level is L3. Normally, a control instruction for adjusting the battery detection frequency to 2 seconds / time and the upper limit of the charge and discharge current to 60A is generated. However, during the use of the battery, there will be a situation of performance degradation. Since a certain value of the battery health state is lost, it may still operate at a relatively high current after reducing the upper limit of the charge and discharge current according to the increase in the risk level. Therefore, in the process of adjusting the upper limit of the charge and discharge current, the available value of the battery health state also needs to be considered. During dynamic adjustment, based on the collected battery state parameters, the available value of the current battery health state is obtained. If the available value is within the preset threshold range (50% - 100%), assume that the current available value of the battery health state is 85%, that is, the loss value of the battery health state is 15%. Therefore, for the current environmental risk level of L3, the adjustment (reduction) of the upper limit of the charge and discharge current is 100A * 60% * (100% - 15%) = 51A. If the available value of the current battery health state is less than the preset threshold, assume it is 45%. At this time, a charge and discharge circuit cut-off instruction is sent to the battery management system to prevent accidents.

[0104] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and the numerical values explained in each step are only for reference explanation to facilitate understanding by those skilled in the art. This is clear to those skilled in the art and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0105] In one of the embodiments, a charge and discharge detection device for a mine-used lithium battery is provided. The charge and discharge detection device for a mine-used lithium battery corresponds to the charge and discharge detection method for a mine-used lithium battery in the above embodiment. The charge and discharge detection device for a mine-used lithium battery includes:

[0106] A data acquisition module for real-time acquisition of mine environmental parameters and lithium battery state parameters. The mine environmental parameters at least include gas concentration, dust density, and vibration frequency. The lithium battery state parameters at least include voltage, current, and temperature;

[0107] An analysis module, configured to obtain historical construction logs, calculate the corresponding construction stages of the mine environmental parameters based on the historical construction logs through time series analysis according to the collected mine environmental parameters;

[0108] A risk assessment module, configured to input the mine environmental parameters and the corresponding construction stages into a trained environmental risk assessment model, and output the current environmental risk level through the environmental risk assessment model;

[0109] A dynamic adjustment module, configured to dynamically adjust the battery detection frequency and the charge and discharge protection threshold according to the lithium battery state parameters and the current environmental risk level, and generate a control instruction including the adjusted parameters;

[0110] A communication switching module, configured to switch the communication protocol based on the environmental risk level, and send the control instruction to the battery management system by using the switched communication protocol.

[0111] Optionally, it further includes:

[0112] A first dynamic adjustment sub-module, configured to forcibly increase the detection frequency and decrease the upper limit of the charge and discharge current when the temperature in the lithium battery state parameters exceeds a first preset threshold;

[0113] A second dynamic adjustment sub-module, configured to trigger a charge and discharge circuit cut-off instruction when the temperature exceeds a second preset threshold.

[0114] Optionally, it further includes:

[0115] A third dynamic adjustment sub-module, configured to, based on the available value of the current battery health state, if the available value is within a preset threshold range and when the environmental risk level increases, increase the detection frequency and decrease the upper limit of the charge and discharge current based on the loss value of the battery health state.

[0116] A fourth dynamic adjustment sub-module, configured to trigger a charge and discharge circuit cut-off instruction if the available value of the current battery health state is less than the preset threshold.

[0117] For the specific limitations of a charge and discharge detection device for a mine-used lithium battery, reference can be made to the limitations on a charge and discharge detection method for a mine-used lithium battery in the above text, which will not be elaborated here. Each module in the above-mentioned charge and discharge detection device for a mine-used lithium battery can be implemented in whole or in part through software, hardware, and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to the above-mentioned modules.

[0118] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structural diagram may be as shown in Figure 2 the figure. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the historical environmental parameters of the mine and their corresponding historical accident data, data processing, etc. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for detecting the charging and discharging of a mine-used lithium battery.

[0119] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements a method for detecting the charging and discharging of a mine-used lithium battery.

[0120] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, it implements a method for detecting the charging and discharging of a mine-used lithium battery.

[0121] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it may include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application may include non-volatile and / or volatile memories. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or an external cache. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0122] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0123] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A charging and discharging detection method for a lithium battery used in mines, characterized in that, Including the following steps: Collecting mine environmental parameters and lithium battery state parameters in real time, where the mine environmental parameters at least include gas concentration, dust density and vibration frequency, and the lithium battery state parameters at least include voltage, current and temperature; Obtaining historical construction logs, and calculating the corresponding construction stages of the mine environmental parameters based on the historical construction logs through time series analysis according to the collected mine environmental parameters; Inputting the mine environmental parameters and the corresponding construction stages into the trained environmental risk assessment model, and outputting the current environmental risk level through the environmental risk assessment model, where the risk level includes level L1 to level L4; Dynamically adjusting the battery detection frequency and charge and discharge protection thresholds according to the lithium battery state parameters and the current environmental risk level, and generating a control instruction including the adjusted parameters; Switching the communication protocol based on the environmental risk level, and sending the control instruction to the battery management system using the switched communication protocol. The communication protocol includes CAN bus communication and LoRa spread spectrum communication. The CAN bus communication is preset as the communication protocol for the L1 to L2 risk levels, and the LoRa spread spectrum communication is preset as the communication protocol for the L3 to L4 risk levels. The switching between the two communication protocols adopts a dual-mode hot standby mechanism; The battery management system receives the control instruction and adjusts the output parameters according to the control instruction. Specifically, adjusting the output parameters according to the control instruction includes: If the real-time current in the collected lithium battery state parameters is within the upper limit threshold range of the charge and discharge current corresponding to the current environmental risk level, and the real-time voltage is within the safety threshold range, the output parameters of the battery management system only include the adjustment of the detection frequency; If the real-time current in the collected lithium battery state parameters is greater than the upper limit threshold of the charge and discharge current corresponding to the current environmental risk level, and the real-time voltage is within the safety threshold range, the output parameters of the battery management system include the adjustment of the detection frequency and the adjustment of the current; Among them, in the step of dynamically adjusting the battery detection frequency and charge and discharge protection thresholds according to the lithium battery state parameters and the current environmental risk level, and generating a control instruction including the adjusted parameters, the detection frequency increases step by step according to the risk level, and the charge and discharge protection thresholds decrease linearly according to the risk level. The dynamic adjustment includes: When the environmental risk level increases, increasing the detection frequency and decreasing the upper limit of the charge and discharge current; When the environmental risk level decreases, decreasing the detection frequency and increasing the upper limit of the charge and discharge current; Based on the available value of the current battery health state, if the available value is within the preset threshold range, and when the environmental risk level increases, increasing the detection frequency and decreasing the upper limit of the charge and discharge current based on the loss value of the battery health state; If the available value of the current battery health state is less than the preset threshold, triggering a charge and discharge circuit cut-off instruction.

2. The charge and discharge detection method of the mine-used lithium battery according to claim 1, characterized in that, In the step of inputting the mine environmental parameters and the corresponding construction stages into the trained environmental risk assessment model, and outputting the current environmental risk level through the environmental risk assessment model, the construction and training of the environmental risk assessment model include the following steps: Collect the historical environmental parameters of the mine, the corresponding historical accident data, and obtain the historical construction logs for preprocessing to obtain standardized feature data applied to the machine model as input data; Use the learning algorithm to train the environmental risk assessment model with the standardized feature data obtained after preprocessing to obtain a trained environmental risk assessment model. Through the trained environmental risk assessment model, it is used to receive the mine environmental parameters and the corresponding construction stages in real time and output the current risk level.

3. The charge and discharge detection method of the mine-used lithium battery according to claim 2, characterized in that, In the step of collecting the historical environmental parameters of the mine, the corresponding historical accident data, and obtaining the historical construction logs for preprocessing to obtain standardized feature data applied to the machine model as input data, the following specific steps are included: Collect the historical environmental parameters of the mine and the corresponding historical accident data, and label the risk level for each historical environmental parameter according to the type and severity of the historical accident data; Perform normalization processing on the labeled historical environmental parameters and historical construction logs to obtain standardized feature data, and the standardized feature data includes at least historical gas concentration, historical dust density, historical vibration frequency, and historical construction logs.

4. The charge and discharge detection method of the mine-used lithium battery according to claim 3, wherein, In the step of using the learning algorithm to train the environmental risk assessment model with the standardized feature data obtained after preprocessing to obtain a trained environmental risk assessment model, and through the trained environmental risk assessment model, which is used to receive the mine environmental parameters and the corresponding construction stages in real time and output the current risk level, the following specific steps are included: Divide the standardized feature data into a training set and a test set; Use the standardized feature data in the training set, take gas concentration, dust density, vibration frequency, and construction logs as input features, and use the random forest algorithm to train the environmental risk assessment model to obtain a trained environmental risk assessment model, and output risk levels L1 to L4; Use the test set to verify the performance of the environmental risk assessment model, require that the recall rate of the L4 level risk is not lower than the preset threshold, and optimize the parameters of the environmental risk assessment model according to the verification results; Based on the optimized environmental risk assessment model, it is used to receive the mine environmental parameters and the corresponding construction stages in real time and output the risk level.

5. The charge and discharge detection method of the mine-used lithium battery according to claim 1, characterized in that, In the step of dynamically adjusting the battery detection frequency and the charge and discharge protection threshold according to the lithium battery state parameters and the current environmental risk level and generating a control command including the adjusted parameters, the dynamic adjustment further includes: When the temperature in the lithium battery state parameters exceeds the first preset threshold, forcibly increase the detection frequency and decrease the upper limit of the charge and discharge current; When the temperature exceeds the second preset threshold, trigger a charge and discharge circuit cut-off command.

6. A charge and discharge detection device for a mine-used lithium battery, which is used to implement the steps of a charge and discharge detection method for a mine-used lithium battery as described in any one of claims 1-5, and is characterized in that, Including: A data acquisition module for real-time collecting mine environmental parameters and lithium battery state parameters. The mine environmental parameters include at least gas concentration, dust density, and vibration frequency, and the lithium battery state parameters include at least voltage, current, and temperature; An analysis module for obtaining historical construction logs, and calculating the corresponding construction stage of the mine environmental parameters based on the historical construction logs through time series analysis according to the collected mine environmental parameters; A risk assessment module, configured to input the mine environment parameters and the corresponding construction stage into a trained environment risk assessment model, and output the current environmental risk level through the environment risk assessment model; A dynamic adjustment module, configured to dynamically adjust the battery detection frequency and the charge and discharge protection threshold according to the lithium battery state parameters and the current environmental risk level, and generate a control instruction including the adjustment parameters; A communication switching module, configured to switch the communication protocol based on the environmental risk level, and send the control instruction to the battery management system by using the switched communication protocol.

7. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, the steps of a charge and discharge detection method for a mine-used lithium battery as described in any one of claims 1-5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the steps of a charge and discharge detection method for a mine-used lithium battery as described in any one of claims 1-5 are implemented.

Images