An artificial intelligence-based lithium battery separator extraction liquid separation and recovery device and method

Abstract

The application discloses a lithium battery diaphragm extraction liquid separation and recovery device and method based on artificial intelligence, relates to the technical field of new energy material manufacturing, and comprises a separation tank, a collection tank, a pump body, a valve body, a sensor group and a control system integrated with a PLC and an AI edge calculation unit, wherein the AI edge calculation unit is embedded with three core models; the AI model is used for dynamically predicting stratification time, adaptively adjusting an electric conductivity threshold value and realizing multi-tank cooperative scheduling, and full-automatic operation is realized. The application not only solves the problems of high energy consumption, low separation precision, poor system cooperativity and much manual intervention of the existing lithium battery diaphragm extraction liquid separation technology, but also greatly shortens a single batch processing cycle, improves separation purity and equipment comprehensive utilization rate, reduces energy consumption and equipment cost, and realizes efficient and high-precision separation and recovery of the extraction liquid.

Description

Technical Field

[0001] This invention relates to the field of new energy material manufacturing technology, and more specifically to an artificial intelligence-based lithium battery separator extract separation and recovery device and method. Background Technology

[0002] Currently, in the wet process of lithium battery separator production, ultra-high molecular weight polyethylene (UHMWPE) base membranes require the removal of pore-forming agents (paraffin oil) through an extractant. Traditional processes use organic solvents such as dichloromethane, which pose safety risks due to high toxicity, flammability, and explosiveness, and their use is restricted by the Stockholm Convention. Novel ionic liquids, due to their high boiling point and low volatility, have become a green alternative, but the separation and recovery of their mixture with paraffin oil faces key challenges: Existing centrifugation / distillation technology: equipment cost 800,000-2,200,000 yuan, energy consumption 15-20 kW·h / m³, and requires manual intervention; Existing automatic stratification technology uses a fixed 30-minute settling time and a fixed conductivity threshold, failing to consider the impact of feed concentration and temperature fluctuations on the stratification rate, resulting in: Incomplete stratification (light phase with residual heavy phase >5%) A fixed conductivity threshold leads to cross-contamination (recurrent phase conductivity fluctuates by ±40 μS / cm). The multi-tank system operates independently, with a capacity utilization rate of less than 65%.

[0003] Therefore, how to provide an intelligent separation and recycling solution that can dynamically predict stratification time, adaptively adjust control thresholds, and achieve multi-tank collaborative scheduling is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] In view of this, the present invention provides an artificial intelligence-based lithium battery separator extract separation and recovery device and method, which solves the problems of high energy consumption, low separation accuracy and poor system coordination in the background technology.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: An artificial intelligence-based lithium battery separator extract separation and recovery device includes: a separation tank, a heavy phase collection tank, a light phase collection tank, a pump body, a valve body, a sensor group, and a control system. The control system includes a PLC and an AI edge computing unit. The AI ​​edge computing unit is bidirectionally connected to the PLC, and the sensor group is signal-connected to the PLC and transmits real-time monitoring data to it. The PLC synchronizes the real-time data from the sensor group to the AI ​​edge computing unit. The pump body and valve body are electrically connected to the PLC. The PLC controls the start-up, shutdown, and operation of the pump body and valve body according to the dynamic control commands from the AI ​​edge computing unit. The inlet of the separation tank is connected to the outlet of the pump body. The heavy phase outlet of the separation tank is connected to the heavy phase collection tank through the valve body, and the light phase outlet of the separation tank is connected to the light phase collection tank through the valve body. The sensor group is deployed on the separation tank for real-time monitoring of relevant parameters of the mixed extract in the separation tank.

[0006] Optionally, the AI ​​edge computing unit embeds a hierarchical time prediction model, an adaptive conductivity threshold model, and a multi-tank collaborative scheduling model; the hierarchical time prediction model outputs a dynamic settling time instruction based on input parameters; the adaptive conductivity threshold model dynamically adjusts the conductivity threshold of the light phase based on real-time temperature data; and the multi-tank collaborative scheduling model generates an optimal feed allocation strategy based on the status of each separation tank, the predicted completion time, and the capacity of the collection tank.

[0007] Optionally, the sensor group includes a temperature sensor, a level gauge, a light phase conductivity sensor, a heavy phase conductivity sensor, and a flow meter. The temperature sensor, level gauge, light phase conductivity sensor, and heavy phase conductivity sensor are all installed on the tank wall of the separator, and the flow meter is installed on the feed pipe of the separator. Each sensor is connected to a PLC signal. Optionally, a buffer tank and a feed pump are also installed on the feed pipe; the buffer tank, feed pump, and flow meter are connected in sequence.

[0008] Optionally, the buffer tank is equipped with a temperature sensor and a level gauge.

[0009] An artificial intelligence-based method for separating and recovering lithium battery separator extract, comprising: S1. Pump the mixed extract into the separation tank; The S2.AI edge computing unit initiates the hierarchical time prediction model and sends a dynamic static time command to the PLC; S3. During the resting period, the PLC collects sensor data in real time and transmits it to the AI ​​edge computing unit; S4. After the settling time is reached, the AI ​​edge computing unit outputs the real-time threshold through the conductivity threshold adaptive model, and the PLC determines whether the conductivity meets the standard. S5. If the target is met, the corresponding valve body will be opened for recovery; if the target is not met, the resting time will be extended or an alarm will be triggered. S6. After recycling is completed, the multi-tank collaborative scheduling model in the AI ​​edge computing unit allocates the next batch to be processed to the optimal separation tank in real time.

[0010] Optionally, the conductivity threshold adaptive model dynamically adjusts the light phase conductivity threshold to <20μS / cm and the heavy phase conductivity threshold to >320μS / cm based on real-time temperature data.

[0011] As can be seen from the above technical solution, compared with the prior art, the present invention discloses an artificial intelligence-based lithium battery separator extract separation and recovery device and method, which has the following beneficial effects: 1. Efficiency Improvement: The tiered time prediction model not only shortens the processing cycle of a single batch, but also increases capacity; 2. Quality Assurance: The adaptive conductivity threshold model ensures that the purity of the light phase is stable at <20 μS / cm (fluctuation ±3 μS / cm) and the purity of the heavy phase is >320 μS / cm (fluctuation ±5 μS / cm). 3. System Collaboration: The multi-tank collaborative scheduling model improves the overall utilization rate of equipment and enables continuous unmanned operation; 4. Energy consumption optimization: Reduced overall energy consumption and equipment costs. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0013] Figure 1 This is a schematic diagram of the device structure provided by the present invention; Figure 2 The overall framework diagram of the control system provided by this invention; Figure 3 This is a schematic diagram of the working principle of the AI ​​edge computing unit provided by the present invention; Figure 4 This is a schematic diagram of the diagnostic process for predictive maintenance of equipment provided by the present invention. Detailed Implementation

[0014] 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.

[0015] This invention discloses an artificial intelligence-based lithium battery separator extract separation and recovery device, such as... Figure 1 and Figure 2 As shown, the system includes: a separation tank, a heavy phase collection tank, a light phase collection tank, a pump body, a valve body, a sensor group, and a control system. The control system includes a PLC and an AI edge computing unit. The AI ​​edge computing unit is bidirectionally connected to the PLC, and the sensor group is signal-connected to the PLC and transmits real-time monitoring data to it. The PLC synchronizes the real-time data from the sensor group to the AI ​​edge computing unit. The pump body and valve body are electrically connected to the PLC. The PLC controls the start-up, shutdown, and operation of the pump body and valve body according to the dynamic control commands from the AI ​​edge computing unit. The inlet of the separation tank is connected to the outlet of the pump body. The heavy phase outlet of the separation tank is connected to the heavy phase collection tank through the valve body, and the light phase outlet of the separation tank is connected to the light phase collection tank through the valve body. The sensor group is installed on the separation tank and is used to monitor the relevant parameters of the mixed extract in the separation tank in real time.

[0016] Specifically, it may include multiple identical separation tanks, and the feed inlet of each separation tank is controlled by a feed valve.

[0017] The heavy phase collection tank and the light phase collection tank are also equipped with thermometers (i.e., temperature sensors) and level gauges.

[0018] In one specific embodiment, the AI ​​edge computing unit embeds a hierarchical time prediction model, a conductivity threshold adaptive model, and a multi-tank collaborative scheduling model. The hierarchical time prediction model outputs a dynamic settling time command based on input parameters. The conductivity threshold adaptive model dynamically adjusts the light phase conductivity threshold based on real-time temperature data. The multi-tank collaborative scheduling model generates an optimal feed allocation strategy based on the status of each separation tank, the predicted completion time, and the capacity of the collection tank. The working principle of the AI ​​edge computing unit is as follows: Figure 3 As shown. The AI ​​edge computing unit also includes diagnostics for predictive maintenance of devices, as illustrated in the flowchart. Figure 4 As shown.

[0019] In one specific embodiment, the sensor group includes a temperature sensor, a level gauge, a light phase conductivity sensor, a heavy phase conductivity sensor, and a flow meter. The temperature sensor, level gauge, light phase conductivity sensor, and heavy phase conductivity sensor are all installed on the wall of the separator, and the flow meter is installed on the feed pipe of the separator. Each sensor is connected to a PLC signal. In another specific embodiment, a buffer tank and a feed pump are also installed on the feed pipe; the buffer tank, feed pump, and flow meter are connected in sequence; the buffer tank contains the temperature sensor and the level gauge.

[0020] Specifically, the input end of the buffer tank is used for raw material feeding, and the feeding is started and stopped through the raw material feeding valve.

[0021] An artificial intelligence-based method for separating and recovering lithium battery separator extract, comprising: S1. Pump the mixed extract into the separation tank; The S2.AI edge computing unit initiates the hierarchical time prediction model and sends a dynamic static time command to the PLC; S3. During the resting period, the PLC collects sensor data in real time and transmits it to the AI ​​edge computing unit; S4. After the settling time is reached, the AI ​​edge computing unit outputs the real-time threshold through the conductivity threshold adaptive model, and the PLC determines whether the conductivity meets the standard. S5. If the target is met, the corresponding valve body will be opened for recovery; if the target is not met, the resting time will be extended or an alarm will be triggered. S6. After recycling is completed, the multi-tank collaborative scheduling model in the AI ​​edge computing unit allocates the next batch to be processed to the optimal separation tank in real time.

[0022] The conductivity threshold adaptive model dynamically adjusts the light phase conductivity threshold to <20μS / cm and the heavy phase conductivity threshold to >320μS / cm based on real-time temperature data.

[0023] Specifically, it also includes the following: Hardware configuration: 4 separation tanks (capacity 1.5m³), temperature sensor accuracy ±0.1℃, AI edge computing unit adopts NVIDIA Jetson AGX Orin (computing power 275TOPS); Model training: Based on 500 batches of historical data (concentration range 15-25%, temperature 25-45℃), the stratified time prediction model was trained using XGBoost (R²=0.96). Workflow: Mixture feed (concentration 20%, temperature 30℃) → AI predicts settling time 18.7 min; After standing for 18.7 min, the AI ​​dynamically adjusted the light phase threshold to 19.2 μS / cm (original fixed value 20 μS / cm). The light phase conductivity of 18.5 μS / cm meets the standard and is automatically recycled to the light phase collection tank; The system schedules the next batch to an idle separation tank to avoid waiting for downtime.

[0024] The comparative experiments are shown in Table 1: Table 1 Comparative Experimental Results

[0025] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0026] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A lithium battery separator extract separation and recovery device based on artificial intelligence, characterized in that, include: The system comprises a separation tank, a heavy phase collection tank, a light phase collection tank, a pump body, a valve body, a sensor group, and a control system. The control system includes a PLC and an AI edge computing unit. The AI ​​edge computing unit is bidirectionally connected to the PLC. The sensor group is signal-connected to the PLC and transmits real-time monitoring data to it. The PLC synchronizes the real-time data from the sensor group to the AI ​​edge computing unit. The pump body and valve body are electrically connected to the PLC. The PLC controls the start, stop, and operation of the pump body and valve body according to the dynamic control commands from the AI ​​edge computing unit. The inlet of the separation tank is connected to the outlet of the pump body. The heavy phase outlet of the separation tank is connected to the heavy phase collection tank via the valve body, and the light phase outlet of the separation tank is connected to the light phase collection tank via the valve body. The sensor group is installed on the separation tank to monitor relevant parameters of the mixed extract solution within the separation tank in real time.

2. The lithium battery separator extract separation and recovery device based on artificial intelligence according to claim 1, characterized in that, The AI ​​edge computing unit embeds a hierarchical time prediction model, an adaptive conductivity threshold model, and a multi-tank collaborative scheduling model. The hierarchical time prediction model outputs a dynamic settling time instruction based on input parameters. The adaptive conductivity threshold model dynamically adjusts the conductivity threshold of the light phase based on real-time temperature data. The multi-tank collaborative scheduling model generates an optimal feed allocation strategy based on the status of each separation tank, the predicted completion time, and the capacity of the collection tank.

3. The lithium battery separator extract separation and recovery device based on artificial intelligence according to claim 1, characterized in that, The sensor group includes a temperature sensor, a level gauge, a light phase conductivity sensor, a heavy phase conductivity sensor, and a flow meter. The temperature sensor, level gauge, light phase conductivity sensor, and heavy phase conductivity sensor are all installed on the tank wall of the separator, and the flow meter is installed on the feed pipe of the separator. Each sensor is connected to the PLC signal.

4. The lithium battery separator extract separation and recovery device based on artificial intelligence according to claim 3, characterized in that, A buffer tank and a liquid inlet pump are also installed on the feed pipeline; the buffer tank, the liquid inlet pump, and the flow meter are connected in sequence.

5. The lithium battery separator extract separation and recovery device based on artificial intelligence according to claim 4, characterized in that, The buffer tank is equipped with a temperature sensor and a level gauge.

6. A method for separating and recovering lithium battery separator extract based on artificial intelligence, characterized in that, An artificial intelligence-based lithium battery separator extract separation and recovery device according to any one of claims 1-5, comprising: S1. Pump the mixed extract into the separation tank; The S2.AI edge computing unit initiates the hierarchical time prediction model and sends a dynamic static time command to the PLC; S3. During the resting period, the PLC collects sensor data in real time and transmits it to the AI ​​edge computing unit; S4. After the settling time is reached, the AI ​​edge computing unit outputs the real-time threshold through the conductivity threshold adaptive model, and the PLC determines whether the conductivity meets the standard. S5. If the target is met, the corresponding valve body will be opened for recovery; if the target is not met, the resting time will be extended or an alarm will be triggered. S6. After recycling is completed, the multi-tank collaborative scheduling model in the AI ​​edge computing unit allocates the next batch to be processed to the optimal separation tank in real time.

7. The method for separating and recovering lithium battery separator extract based on artificial intelligence according to claim 6, characterized in that, The conductivity threshold adaptive model dynamically adjusts the light phase conductivity threshold to <20μS / cm and the heavy phase conductivity threshold to >320μS / cm based on real-time temperature data.

Images