Gas sensor, method of preparation, method of detection and thermal runaway monitoring method

Abstract

The application relates to a MOFs-based gas sensor, a preparation method, a detection method and a thermal runaway monitoring method, comprising: a plurality of sensing units, each sensing unit comprising: a silicon substrate layer; a nanostructure located on the surface of the silicon substrate layer; a MOFs gas-sensitive layer covering the surface of the nanostructure, used for adsorbing a target gas and chemically reacting with the adsorbed target gas through a MOFs material to cause a change in an electric signal; an interdigital electrode located on the surface of the silicon substrate layer and used for amplifying the change in the electric signal based on an electric field distribution; and a packaging layer covering the sensing unit; wherein the packaging layer has a porous structure allowing gas to permeate. The gas sensor provided by the application has the characteristics of high sensitivity and fast response speed and can effectively detect the types and concentrations of gases.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of gas sensors, in particular to a MOFs-based gas sensor, a preparation method, a detection method and a thermal runaway monitoring method. BACKGROUND

[0002] With the rapid development of new energy vehicles, lithium batteries have become an important energy source in the fields of electric vehicles, energy storage systems, etc. due to their high energy density and long cycle life. However, lithium batteries are prone to thermal runaway under conditions such as overcharging and short circuit, and will rapidly release gases such as CO, H2, CH4 and C2H4. The concentration change of these gases can be used as an early warning signal of thermal runaway. Therefore, it is crucial to quickly and accurately detect these gases to improve the safety of lithium batteries.

[0003] Currently, the sensors for gas detection mainly include infrared gas sensors, electrochemical gas sensors and semiconductor gas sensors. For infrared gas sensors, they mainly detect based on the absorption characteristics of gas molecules to specific infrared wavebands. However, such sensors rely on optical systems, which makes the overall volume of the sensor large and the cost high, making it difficult to integrate with lithium battery packs, and the sensitivity to low-concentration gases is insufficient. For electrochemical gas sensors, they mainly measure gas concentration based on electrochemical reactions. However, the electrolyte of such sensors is prone to evaporation, and the electrode is prone to passivation, resulting in a short service life (usually less than two years), which cannot meet the long-term monitoring of battery gas leakage. For semiconductor gas sensors, they need to be operated at a high temperature of 200-400℃ to fully exhibit their sensing characteristics, which not only increases energy consumption, but also may interfere with the battery's thermal management system due to high temperature, increasing additional use risks. In addition, the existing gas sensors also have problems such as slow response speed (response time > 10 seconds) and insufficient multi-gas simultaneous detection capability. However, the thermal runaway process of lithium batteries is sudden and rapidly spreading, and the existing gas sensors are difficult to capture the mutation signal of gas concentration in time, which may cause delay in early warning and cause irreparable loss. SUMMARY

[0004] In view of the above problems of the prior art, the present application provides a MOFs-based gas sensor, a preparation method, a detection method and a thermal runaway monitoring method. The gas sensor has the advantages of small volume, long service life, high sensitivity, fast response speed and support for multi-gas simultaneous detection.

[0005] To achieve the above object, the first aspect of the present application provides a MOFs-based gas sensor, comprising: a plurality of sensing units, each of which comprises: a silicon substrate layer; a nanostructure located on the surface of the silicon substrate layer; a MOFs gas-sensitive layer covering the surface of the nanostructure, used for adsorbing target gas and chemically reacting with the adsorbed target gas through MOFs material to cause a change in electrical signal; an interdigital electrode located on the surface of the silicon substrate layer, used for amplifying the change in electrical signal based on the distribution of electric field; and a packaging layer covering the sensing unit; wherein the packaging layer has a porous structure allowing gas to permeate.

[0006] From the above, through the above-mentioned gas sensor, when in an environment with target gas, the MOFs material in the MOFs gas-sensitive layer reacts with the target gas, thereby causing a change in the electrical signal of the interdigital electrode to realize gas detection. The gas sensor has small volume, long service life, high sensitivity and fast response speed. Since the sensor includes a plurality of sensing units, each of which is made of different MOFs material, it can support synchronous detection of multiple gases.

[0007] As an implementation manner of the present aspect, the gas-sensitive layer of the plurality of sensing units is made of different MOFs material doped with different metal oxides.

[0008] As an implementation manner of the present aspect, the plurality of sensing units include: a first sensing unit, a second sensing unit, a third sensing unit, a fourth sensing unit, a fifth sensing unit and / or a sixth sensing unit; the gas-sensitive layer of the first sensing unit is made of ZIF-8 doped with SnO2; the gas-sensitive layer of the second sensing unit is made of HKUST-1 doped with ZnO; the gas-sensitive layer of the third sensing unit is made of MOF-74(Ni) doped with WO3; the gas-sensitive layer of the fourth sensing unit is made of UiO-66 doped with TiO2; the gas-sensitive layer of the fifth sensing unit is made of MIL-101(Cr) doped with Fe2O3; and the gas-sensitive layer of the sixth sensing unit is made of ZIF-67 doped with Co3O4.

[0009] From the above, different sensing units are made of different materials, thereby realizing synchronous detection of multiple gases.

[0010] As an implementation manner of the present aspect, the nanostructure includes: a nanoarray composed of a plurality of nanocolumns, a nanoarray composed of a plurality of nanowires or a nanoarray composed of a plurality of nanopores; wherein in the nanoarray, the ratio of the height and width of each nanomonomer exceeds a first threshold value.

[0011] Therefore, by setting a nanostructure with a large aspect ratio, the surface area of the MOFs gas-sensitive layer can be increased, thereby improving the adsorption capacity.

[0012] As an implementation manner of the present aspect, the detection device is further connected with the interdigital electrode, and is configured to determine the concentration and the type of the target gas based on the change of the electrical signal. The detection device comprises: a signal acquisition unit configured to acquire electrical signals of a plurality of data channels based on a preset sampling frequency to generate time series data sets of the plurality of data channels, wherein different data channels correspond to different sensing units, and different data channels correspond to different time series data sets; a signal preprocessing unit configured to perform signal denoising processing and normalization processing on the time series data sets of the plurality of data channels respectively to obtain a plurality of standardized time series data sets; a feature extraction unit configured to extract a feature sequence of each of the plurality of standardized time series data sets based on a convolutional neural network; a gas recognition unit configured to determine a target gas type probability and a target gas concentration prediction value corresponding to the feature sequence based on a long short-term memory network, and determine the gas type with the largest probability as the detected gas type and the gas concentration prediction value as the detected gas concentration; and an early warning unit configured to issue different levels of early warning signals according to the concentration and the type of the target gas.

[0013] As described above, the detection method can improve the detection accuracy and the detection speed.

[0014] The second aspect of the present application provides a preparation method of a gas sensor, comprising: making a gold mask plate on a silicon substrate layer by a photolithography technology, and etching other regions on the silicon substrate layer by a metal-assisted etching technology to obtain a nanostructure, wherein the other regions include regions not covered by the gold mask plate; in-situ synthesizing an initial MOFs gas-sensitive layer on the nanostructure by a layer-by-layer deposition method using MOFs material and metal oxide, and performing high-temperature activation on the initial MOFs gas-sensitive layer in an inert gas environment to obtain a final MOFs gas-sensitive layer; making an interdigital electrode on the silicon substrate layer by an electron beam evaporation technology and a photolithography technology; and covering a porous structure with a gas permeable structure on the surface of the sensing unit as an encapsulation layer by a plasma-enhanced chemical vapor deposition technology.

[0015] As an implementation manner of the present aspect, the MOFs material is made by a solvothermal melting method.

[0016] As an implementation manner of the present aspect, the interdigital electrode is connected with the detection device by a gold wire bonding process to output an electrode signal.

[0017] The beneficial effects of the present aspect can also be seen from the description of the beneficial effects of each part of the first aspect.

[0018] The third aspect of the present application provides a method for detecting gas by using the sensor of any one of the first aspect, comprising: collecting electrical signals of multiple data channels based on a preset sampling frequency to generate time series data sets of the multiple data channels, wherein different data channels correspond to different sensing units, and different data channels correspond to different time series data sets; performing signal denoising processing and normalization processing on the time series data sets of the multiple data channels respectively to obtain multiple standardized time series data sets; extracting feature sequences of the multiple standardized time series data sets based on a convolutional neural network, and determining gas species probability and gas concentration prediction value corresponding to the feature sequences based on a long short-term memory network; determining the gas species with the maximum probability as the detected gas species, and taking the gas concentration prediction value as the detected gas concentration.

[0019] The beneficial effects of the present aspect can also be seen from the description of the beneficial effects of each part of the first aspect.

[0020] The fourth aspect of the present application provides a method for monitoring thermal runaway of a lithium battery, comprising: monitoring the gas species and the gas concentration released by the lithium battery by using the MOFs-based gas sensor of any one of the first aspect, and determining whether the lithium battery has a thermal runaway phenomenon according to the gas species and the gas concentration.

[0021] The beneficial effects of the present aspect can also be seen from the description of the beneficial effects of each part of the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0022] The various technical features of the present application and the relationship between them will be further described below with reference to the accompanying drawings. The drawings are exemplary, some technical features are not shown in actual proportion, and some technical features in the drawings can be omitted, which are conventional in the technical field to which the present application belongs and are not essential for understanding and implementing the present application, or additional technical features are shown, which are not essential for understanding and implementing the present application, that is, the combination of various technical features shown in the drawings is not used to limit the present application. In addition, the same reference signs refer to the same contents throughout the present application. The specific drawings are as follows:

[0023] Figure 1a A perspective structural schematic diagram of the MOFs-based gas sensor provided by the embodiments of the present application is shown;

[0024] Figure 1b An enlarged view of the perspective structure of the MOFs-based gas sensor provided by the embodiments of the present application is shown;

[0025] Figure 2An example diagram of a MOFs-based gas sensor including a plurality of sensing units is provided in embodiments of the present application.

[0026] Figure 3a A schematic diagram of a preparation process of a nanostructure is provided in embodiments of the present application.

[0027] Figure 3b A schematic diagram of a preparation process of a MOFs gas-sensitive layer is provided in embodiments of the present application.

[0028] Figure 4 A flowchart of a gas detection method is provided in embodiments of the present application. DETAILED DESCRIPTION

[0029] The technical solutions provided in the present application will be further described in conjunction with the accompanying drawings and embodiments. It should be understood that the sensor structures and service scenarios provided in the embodiments of the present application are mainly used to illustrate possible implementation manners of the technical solutions of the present application, and should not be interpreted as the only limitation of the technical solutions of the present application. Those skilled in the art can know that the technical solutions provided in the present application are also applicable to similar technical problems as the sensor structure evolves and new service scenarios appear.

[0030] It should be understood that the embodiments of the present application provide a MOFs-based gas sensor scheme. Since the principles of these technical solutions for solving problems are the same or similar, in the following introduction of specific embodiments, some repeated parts may not be described again, but should be regarded as mutual reference between these specific embodiments, which can be combined with each other.

[0031] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. If there is any inconsistency, the meaning explained in the specification or derived from the content described in the specification shall prevail. In addition, the terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0032] The MOFs-based gas sensor scheme provided in the present application is mainly used in the field of monitoring lithium battery thermal runaway. During the process of lithium battery thermal runaway, gases such as CO, H2, CH4, C2H4, etc. are rapidly released, and the concentration change is earlier than the temperature change, which is the key signal for early warning of thermal runaway. Therefore, the MOFs-based gas sensor is integrated into the lithium battery module or battery management system, and different sensing units in the sensor detect different types of gases, which not only realizes the synchronous detection of multiple gases, but also improves the detection sensitivity and response speed, thereby providing real-time and accurate monitoring for lithium battery thermal runaway.

[0033] Embodiments of the present application provide a MOFs-based gas sensor, which will be described below in conjunction withFigure 1a , Figure 1b and Figure 2 The gas sensor is described in detail. Among them, Figure 1a is a schematic diagram of the gas sensor, Figure 1b is an enlarged view of the gas sensor, Figure 2 is a schematic diagram of the gas sensor including a plurality of sensing units.

[0034] As shown in Figure 1a , Figure 1b and Figure 2 , the gas sensor includes a plurality of sensing units (for example, the first sensing unit a to the sixth sensing unit f shown in Figure 2 ), each of which includes a silicon substrate layer 110, a nanostructure 120, a MOFs gas sensitive layer 130, an interdigital electrode 140, and a packaging layer (in order to show the structure of each layer of the sensor, the packaging layer is not shown). In this embodiment, the gas sensor also includes a detection device (not shown). Among them, the plurality of sensing units can share the same silicon substrate layer 110 and the same packaging layer; of course, the plurality of sensing units can also be provided with independent silicon substrate layers 110 and independent packaging layers. In addition, the plurality of sensing units can share the same detection device, or each sensing unit can be connected to an independent detection device. Next, the structures of the gas sensor are described in detail.

[0035] The silicon substrate layer 110 is used to provide support for each sensing unit.

[0036] The nanostructure 120 is located on the surface of the silicon substrate layer 110. The nanostructure 120 can be a nanoarray structure composed of a plurality of nanocolumns, a nanoarray structure composed of a plurality of nanowires, or a nanoarray structure composed of a plurality of nanopores, etc. In this embodiment, since the nanostructure 120 is the carrier of the MOFs gas sensitive layer 130, in order to increase the surface area to enhance the adsorption capacity of gas molecules, the ratio of the height and width of each nanomonomer (nanomonomer refers to a single nanocolumn, a single nanowire, or a single nanopore in the nanoarray) in this embodiment is set to exceed a first threshold value, for example, the first threshold value can be in the range of 10:1 to 50:1, and preferably 20:1, that is, the ratio of the height and width of each nanomonomer is set to 20:1. Specifically, the width (which can also be referred to as the diameter) of each nanomonomer can be set to be in the order of hundreds of nanometers (for example, about 100 nanometers), the height of each nanomonomer can be set to be in the order of micrometers (for example, about 2 μm), and the spacing between different nanomonomers in the same nanoarray can be set to be between 100 nm and 500 nm. In this embodiment, the spacing is set to 200 nm.

[0037] The MOFs gas sensitive layer 130 covers the surface of the nano structure 120, for adsorbing target gas and causing chemical reaction between the MOFs material and the adsorbed target gas, so as to cause the change of the electric signal (such as resistivity, current, inductance, etc.). In the embodiment, the gas sensitive layer of different sensing units in the sensor is made of different MOFs material doped with different metal oxide. For example:

[0038] (1) For the first sensing unit a, the gas sensitive layer thereof is made of ZIF-8 doped with SnO2, which can be used to adsorb (detect) gas such as CO, H2, etc.

[0039] (2) For the second sensing unit b, the gas sensitive layer thereof is made of HKUST-1 doped with ZnO, which can be used to adsorb gas such as H2, CH4, etc.

[0040] (3) For the third sensing unit c, the gas sensitive layer thereof is made of MOF-74(Ni) doped with WO3, which can be used to adsorb gas such as CH4, H2, etc.

[0041] (4) For the fourth sensing unit d, the gas sensitive layer thereof is made of UiO-66 doped with TiO2, which can be used to adsorb gas such as C2H4, CO, etc.

[0042] (5) For the fifth sensing unit e, the gas sensitive layer thereof is made of MIL-101(Cr) doped with Fe2O3, which can be used to adsorb gas such as C2H4, CH4, etc.

[0043] (6) For the sixth sensing unit f, the gas sensitive layer thereof is made of ZIF-67 doped with Co3O4, which can be used to adsorb gas such as H2, CO, etc.

[0044] The interdigital electrode 140 is located on the surface of the silicon substrate layer 110, for amplifying the change of the electric signal based on its own electric field distribution, so as to improve the detection sensitivity. In the embodiment, the electrode width of the interdigital electrode 140 can be set to be between 3 μm and 10 μm, and the interval between the two electrodes can be set to be between 2 μm and 8 μm. In the embodiment, the electrode width of the interdigital electrode 140 is set to be 5 μm, the electrode interval is set to be 3 μm, the number of electrode pairs is 6, and the electrode material is platinum (Pt).

[0045] The packaging layer covers the sensing unit, in order to enable the gas to contact the MOFs gas sensitive layer 130 through the packaging layer, the packaging layer is selected to have porous structure allowing the gas to pass through in the embodiment, for example, porous SiO2 film (for example, thickness 500 nm, pore size 0.8 μm) is selected. The packaging layer can protect the MOFs gas sensitive layer 130, and prevent dust interference on the premise of allowing the gas to pass through. In the embodiment, the electrode signal of the interdigital electrode 140 can be led out through the process of gold wire bonding.

[0046] The detection device is connected with the interdigital electrode 140, and is used for determining the concentration and type of the target gas based on the detected change of the electrical signal. The detection device includes a signal acquisition unit, a signal preprocessing unit, a feature extraction unit, a gas recognition unit and a warning unit. Specifically, the signal acquisition unit is used for acquiring electrical signals of multiple data channels based on a preset sampling frequency to generate time series data sets of the multiple data channels, wherein different data channels correspond to different sensing units, and different data channels correspond to different time series data sets; the signal preprocessing unit is used for respectively performing signal denoising processing and normalization processing on the time series data sets of the multiple data channels of the sensing unit to obtain multiple standardized time series data sets; the feature extraction unit is used for extracting feature sequences of the multiple standardized time series data sets of the sensing unit based on a convolutional neural network; the gas recognition unit is used for determining a target gas type probability and a target gas concentration prediction value corresponding to the feature sequence of the sensing unit based on a long short-term memory network, and determining a gas type with the largest probability of the sensing unit as the detected gas type and a gas concentration prediction value of the sensing unit as the detected gas concentration; and the warning unit is used for issuing different levels of warning signals according to the concentration and type of the target gas of the sensing unit. The specific gas detection process can be referred to the detailed description of the gas detection part below.

[0047] The gas sensor provided by the embodiment of the present application can cause the MOFs material in the MOFs gas-sensitive layer to react with the target gas when the target gas exists in the environment, so as to cause the change of the electrical signal of the interdigital electrode, thereby realizing the rapid detection of the gas. In addition, the sensor of the embodiment includes multiple sensing units, each of which is made of different MOFs materials, so that multiple gases can be detected synchronously.

[0048] Next, the preparation method of the gas sensor will be introduced in combination with Figure 3a and Figure 3b The preparation method includes the following steps:

[0049] A: preparing the nano structure 120: as shown in Figure 3a , a gold mask plate is made on the silicon substrate layer 110 by a photolithography technology, and other regions on the silicon substrate layer 110 are etched by a metal-assisted etching (MacEtch) technology to obtain the nano structure 120, wherein the other regions include regions not covered by the gold mask plate.

[0050] B: preparing the MOFs gas-sensitive layer 130: as shown in Figure 3b , the MOFs material is first prepared by a solvothermal melting method, and the MOFs material and the metal oxide are in-situ synthesized into an initial MOFs gas-sensitive layer on the nano structure 130 by a layer-by-layer deposition method, for example Figure 3bAs shown, a layer of metal oxide is first sprayed onto the nanostructure 120 to form a metal central site layer, followed by the spraying of a layer of MOF material to form a ligand layer… After repeatedly constructing the initial MOF gas-sensitive layer, the initial MOF gas-sensitive layer is activated at high temperature in an inert gas environment (e.g., nitrogen (N2), argon (Ar), helium (He)) to obtain the final stable MOF gas-sensitive layer 130. The high-temperature activation temperature can be 300℃ to 500℃, and the activation time can be 30 minutes to 60 minutes. In this embodiment, the temperature is 400℃ and the time is 45 minutes.

[0051] C: Fabrication of interdigitated electrodes 140: Interdigitated electrodes 140 are fabricated by depositing a 100 nm platinum (Pt) thin film on the surface of the silicon substrate 110, followed by electron beam evaporation and photolithography. Furthermore, the interdigitated electrodes 140 require gold wire bonding to extract electrode signals for connection to the detection device.

[0052] D: Fabrication of the encapsulation layer: A porous structure that allows gas permeation is coated onto the surface of the sensing unit as an encapsulation layer using plasma-enhanced chemical vapor deposition (PECVD). In this embodiment, the encapsulation layer can be, for example, a porous SiO2 film (500 nm thick, 0.8 μm pore size).

[0053] Next, combine Figure 4 This paper introduces the method (i.e., detection principle) for gas detection using this gas sensor. The method mainly includes three steps: S410 data acquisition and preprocessing, S420 feature extraction, and S430 time series analysis. Specifically:

[0054] In the S410 data acquisition and preprocessing steps: the sensor is placed in the environment to be tested. When the target gas is present in the environment, the MOF gas-sensitive layer of the sensor comes into contact with the target gas and undergoes a chemical reaction, which causes the electrical signal of the interdigitated electrode to change. The interdigitated electrode amplifies the change in electrical signal through its own electric field distribution. Then, the detection device connected to the interdigitated electrode synchronously acquires the electrical signals of multiple data channels based on a preset sampling frequency to generate time series datasets of multiple data channels. Different data channels correspond to different sensing units, and different data channels correspond to different time series datasets.

[0055] One approach is to store the collected real-time data (i.e., time-series datasets from multiple data channels) for later use.

[0056] Then, signal denoising and normalization processes were performed on the time series datasets from multiple data channels to obtain multiple standardized time series datasets.

[0057] In the feature extraction step S420: based on a convolutional neural network (CNN), the respective feature sequence of each standardized time series data set is extracted.

[0058] In the time series analysis step S430: based on a long short-term memory network (LSTM), the gas species probability and gas concentration prediction value corresponding to the feature sequence are determined, and the gas species with the highest probability is determined as the detected gas species, and the gas concentration prediction value is taken as the detected gas concentration.

[0059] In order to better understand the detection algorithm, a specific example is given below.

[0060] First, a gas detection model is constructed, which is based on a convolutional neural network (CNN) and a long short-term memory model (LSTM). The training data set of the gas detection model is the response data (or response pattern) of the sensor under different concentrations of different gases, and the gas detection model is trained through the training data set.

[0061] Next, the process of detecting the gas species and gas concentration through the gas detection model is introduced:

[0062] S410 data acquisition and preprocessing:

[0063] (1) Data acquisition:

[0064] Input: resistance change rate signal of each sensing unit (ΔR / R0, where R0 is the initial resistance value and ΔR is the real-time resistance change amount);

[0065] Acquisition tool: 16-bit analog-to-digital converter (ADC), sampling frequency set to 100 Hz, input voltage range 0-5V;

[0066] Output: generate time series data sets including each sensing unit, each sensing unit collects 100 data points per second, a total of 600 data points for 6 seconds, and 6*600 data points for 6 sensing units.

[0067] (2) Signal denoising:

[0068] Method: wavelet transform, specific parameters as follows: wavelet base function: Daubechies wavelet; decomposition level: 3 layers; denoising threshold setting: Where σ is the noise standard deviation and N is the number of sampling points (N=600 for each sensing unit corresponding data set);

[0069] Output: denoised smooth time series, retaining gas response characteristics and suppressing environmental noise.

[0070] (3) Normalization:

[0071] Method: Linearly map the denoised signal to the interval [0, 1] using Min-Max normalization.

[0072] Output: Normalized time series set, eliminating dimensional differences between sensor units, improving convergence efficiency.

[0073] S420 Feature Extraction:

[0074] (1) Data Reorganization:

[0075] Input: Normalized time series set of multiple sensor units (data points: 6*600);

[0076] Method: Convert the normalized time series set of multiple sensor units into a two-dimensional matrix with dimensions of sensor unit number * sampling point number of each sensor unit (e.g. 6*600);

[0077] Output: Two-dimensional tensor, adapting to the input format of convolutional neural network (CNN).

[0078] (2) Convolutional Neural Network (CNN) Feature Extraction:

[0079] Network Architecture: 3-layer convolutional neural network, specific parameters as follows:

[0080] First convolutional layer: 32 3x1 convolutional kernels, stride 1, activation function ReLU;

[0081] First pooling layer: 2x1 max pooling, stride 2;

[0082] Second convolutional layer: 64 3x1 convolutional kernels, stride 1, activation function ReLU;

[0083] Second pooling layer: 2x1 max pooling, stride 2;

[0084] Third convolutional layer: 128 3x1 convolutional kernels, stride 1, activation function ReLU;

[0085] Output: After convolution and pooling operations, generate three-dimensional spatial feature map (dimension: 1, 128, 146).

[0086] (3) Feature Sequence Tiling Processing:

[0087] Method: Tile the three-dimensional feature map (1, 128, 146) output by CNN according to time steps, with dimensions (1, 146, 128).

[0088] Output: Three-dimensional tensor (dimension: 1, 146, 128), adapting to the time series modeling requirements of long short-term memory network (LSTM).

[0089] S430 time series analysis (LSTM):

[0090] (1) LSTM network architecture:

[0091] A 2-layer LSTM network is used, with 64 units in each layer, and the activation function: tanh function for hidden state, sigmoid function for gating unit; Regularization: Dropout ratio is 0.2 to prevent overfitting.

[0092] Input data: feature sequence extracted by CNN;

[0093] Output result: time series hidden state sequence (dimension: 1, 64);

[0094] (2) Fully connected layer:

[0095] Input: time series hidden state sequence output by LSTM (dimension: 1, 64);

[0096] Output layer: number of neurons equal to number of gas categories + number of concentration levels;

[0097] Activation function: Softmax for output gas species probability distribution; activation function Linear for output gas concentration prediction value;

[0098] Output result: gas species probability distribution and gas concentration prediction value.

[0099] (3) Classification and regression:

[0100] For gas species: output the class with the highest probability as the gas species;

[0101] For gas concentration: output the gas concentration predicted by Linear as the gas concentration.

[0102] In this embodiment, a sliding window technique can also be used to update the input data. For example: update the input data every 0.5 seconds, thereby increasing the real-time nature of the data and ensuring the timeliness of the detection.

[0103] The detection algorithm of S410-S430 in the above example improves the speed of recognizing gas through the hybrid model of CNN-LSTM.

[0104] The embodiments of the present application also provide a method for detecting thermal runaway of a lithium battery, comprising: integrating the sensor described above with a battery management system, using the sensor to monitor the gas species and gas concentration released by the lithium battery in real time, and determining whether the lithium battery has a thermal runaway phenomenon according to the gas species and the gas concentration. For example: when the concentration of a certain gas is detected to be higher than a preset concentration (such as CO>50ppm and / or H2>100ppm), a graded alarm is automatically triggered.

[0105] It is to be understood that the above description is merely a preferred embodiment of the application and the applied technical principles. Those skilled in the art will understand that the application is not limited to the specific embodiments described herein, and that various obvious changes, modifications and substitutions can be made without departing from the scope of the application. Therefore, although the application has been described in detail through the above embodiments, the application is not limited to the above embodiments, and more other equivalent embodiments can be included without departing from the concept of the application, and all belong to the protection scope of the application.

Claims

1. A MOFs-based gas sensor, characterized in that, Comprise: a plurality of sensing units, each sensing unit comprising: a silicon substrate layer; nanostructures on the surface of the silicon substrate layer; a MOFs gas sensing layer covering the surface of the nanostructures, for adsorbing target gas and causing a change in electrical signal by chemical reaction between the MOFs material and the adsorbed target gas; interdigital electrodes on the surface of the silicon substrate layer, for amplifying the change in electrical signal based on the distribution of electric field; an encapsulation layer covering the sensing units; wherein the encapsulation layer has a porous structure allowing gas to pass through; the gas sensing layers of the plurality of sensing units are made of different MOFs materials doped with different metal oxides; the plurality of sensing units comprise: a first sensing unit, a second sensing unit, a third sensing unit, a fourth sensing unit, a fifth sensing unit, and / or a sixth sensing unit; the gas sensing layer of the first sensing unit is made of ZIF-8 doped with SnO2; the gas sensing layer of the second sensing unit is made of HKUST-1 doped with ZnO; the gas sensing layer of the third sensing unit is made of MOF-74 doped with WO3; the gas sensing layer of the fourth sensing unit is made of UiO-66 doped with TiO2; the gas sensing layer of the fifth sensing unit is made of MIL-101 doped with Fe2O3; the gas sensing layer of the sixth sensing unit is made of ZIF-67 doped with Co3O4.

2. The gas sensor according to claim 1, characterized by The MOF-74 has Ni as a central metal ion.

3. The gas sensor according to claim 1, characterized by The MIL-101 has Cr as a central metal ion.

4. The gas sensor according to claim 1, characterized by The nanostructures comprise: a nanoarray composed of a plurality of nanocolumns, a nanoarray composed of a plurality of nanowires, or a nanoarray composed of a plurality of nanopores; wherein in the nanoarray, the ratio of the height and width of each nanomonomer exceeds a first threshold value; the first threshold value ranges from 10:1 to 50:

1.

5. The gas sensor according to claim 1, characterized by Further comprising: a detection device connected to the interdigital electrodes; the detection device is used to determine the concentration and type of the target gas based on the change in the electrical signal; the detection device comprises: a signal acquisition unit for acquiring electrical signals of a plurality of data channels based on a preset sampling frequency to generate time series data sets of a plurality of data channels, wherein different data channels correspond to different sensing units, and different data channels correspond to different time series data sets; a signal preprocessing unit for respectively performing signal denoising processing and normalization processing on the time series data sets of the plurality of data channels to obtain a plurality of standardized time series data sets; a feature extraction unit for extracting a feature sequence of each of the plurality of standardized time series data sets based on a convolutional neural network; a gas recognition unit for determining a target gas type probability and a target gas concentration prediction value corresponding to the feature sequence based on a long short-term memory network, and determining the gas type with the largest probability as the detected gas type and the gas concentration prediction value as the detected gas concentration; a warning unit for issuing different levels of warning signals according to the concentration and type of the target gas.

6. A method of producing the gas sensor according to any one of claims 1 to 5, characterized by, Comprise: A gold mask plate is made on a silicon substrate layer by a photolithography technology, and a metal-assisted etching technology is used to etch other regions on the silicon substrate layer to obtain a nanostructure, the other regions including regions not covered by the gold mask plate; An initial MOFs gas-sensitive layer is in-situ synthesized on the nanostructure by a layer-by-layer deposition method, and the initial MOFs gas-sensitive layer is activated at high temperature in an inert gas environment to obtain a final MOFs gas-sensitive layer; An interdigital electrode is made on the silicon substrate layer by an electron beam evaporation technology and a photolithography technology; A porous structure with gas permeability is covered on the surface of the sensing unit as an encapsulation layer by a plasma-enhanced chemical vapor deposition technology.

7. The method of claim 6, wherein, The MOFs material is made by a solvothermal melting method.

8. The method of claim 6, wherein, The interdigital electrode is connected to a detection device by a gold wire bonding process to output electrode signals.

9. A method for gas detection using the sensor according to any one of claims 1 to 5, characterized in that, The method comprises: Based on a preset sampling frequency, collecting electrical signals of multiple data channels to generate time series data sets of the multiple data channels, wherein different data channels correspond to different sensing units, and different data channels correspond to different time series data sets; Respectively performing signal denoising processing and normalization processing on the time series data sets of the multiple data channels to obtain multiple standardized time series data sets; Based on a convolutional neural network, extracting feature sequences of the multiple standardized time series data sets, and based on a long short-term memory network, determining gas species probability and gas concentration prediction value corresponding to the feature sequences; The gas species with the maximum probability is determined as the detected gas species, and the gas concentration prediction value is used as the detected gas concentration.

10. A method of detecting thermal runaway of a lithium battery, the method comprising: The method comprises: The MOFs-based gas sensor according to any one of claims 1-5 is used to monitor the gas species and gas concentration released by a lithium battery, and whether the lithium battery has a thermal runaway phenomenon is determined according to the gas species and the gas concentration.

Images