Passive detection of thermal runaway using acoustic waves

Abstract

The invention relates to passive detection of thermal runaway using acoustic waves, in particular to a computer system (100) comprising processing circuitry (102) configured to: receive sensing data (D) from at least one sensor (104) arranged to detect acoustic waves emitted from an electrical energy storage cell (106) of an electrical energy storage system (108), the sensing data is indicative of at least one characteristic of an acoustic wave; applying an algorithm (110) configured to predict a thermal runaway event by analyzing the sensed data; if the result of the analysis is that a thermal runaway is predicted, a message (W) is provided.

Description

Technical Field

[0001] The present disclosure generally relates to electrical energy storage systems. In particular aspects, the present disclosure relates to passive detection of thermal runaway using acoustic waves. The present disclosure may be applied to heavy vehicles such as trucks, buses, and construction equipment, as well as other vehicle types. In addition, the present invention may also be applicable to stationary applications and marine applications. Although the present disclosure may be described with respect to a particular vehicle, the present disclosure is not limited to any particular vehicle. Background Art

[0002] A thermal runaway event of a vehicle's electrical energy storage system is dangerous to the vehicle's occupants and surrounding personnel. In addition, a thermal runaway event may cause damage to the vehicle and may cause damage to objects in the vicinity of the vehicle.

[0003] The safety functions currently implemented on energy storage systems usually rely heavily on temperature sensors or thermocouples arranged on the internal structure or cells of the energy storage system. However, for an effective warning system, the warning should be early enough so that preventive measures or safety measures can be taken before a thermal runaway event actually occurs and overheating occurs. Summary of the invention

[0004] According to a first aspect of the present disclosure, a computer system is provided, comprising a processing circuit, wherein the processing circuit is configured to: receive sensing data from at least one sensor arranged to detect acoustic waves emitted from an energy storage cell of an energy storage system, the sensing data indicating at least one characteristic of the acoustic waves; apply an algorithm configured to predict a thermal runaway event by analyzing the sensing data; and provide a message if a result of the analysis is that thermal runaway is predicted.

[0005] A first aspect of the present disclosure may seek to improve detection of thermal runaway events in an electrical energy storage system. Technical benefits may include earlier detection, which allows more time and opportunity to take action in response to a predicted thermal runaway event.

[0006] Optionally, in some examples, including at least one preferred example, the algorithm may be a machine learning model trained to predict thermal runaway events based on detecting acoustic waves generated by bubbles in an energy storage cell. Technical benefits may include improved ability to detect thermal runaway events earlier and more accurately.

[0007] Optionally, in some examples, including at least one preferred example, the machine learning model can be a supervised learning model that is trained on acoustic data from test cells to create a fingerprint library of characteristic sounds of thermal runaway events. Technical benefits can include improved models for predicting thermal runaway events.

[0008] Optionally, in some examples, including at least one preferred example, the processing circuit can be further configured to predict a thermal runaway event by analyzing acoustic waves at a characteristic frequency of electrolyte boiling before the thermal runaway event. "Before" the thermal runaway event means close to or just a few minutes before the thermal runaway event occurs, such as 10-15 minutes.

[0009] For example, the processing circuit can be configured to analyze acoustic waves at frequencies below 5 kHz, such as in the range of 1-2 kHz, or below 500 Hz. Technical benefits can include the ability to detect acoustic waves specifically generated by bubbles in an energy storage cell. Thus, the algorithm can filter out frequencies that are not relevant to detecting thermal runaway events by analyzing the acoustic dynamics of the bubbles. The source of the acoustic waves is one or more of bubble formation, bubble movement, bubble collapse, and resonance thereof.

[0010] Optionally, in some examples, including at least one preferred example, the processing circuit can be configured to wirelessly receive the sensing data from a transmitter connected to the sensor.Technical benefits can include less complex integration due to reduced or eliminated use of hard wires.

[0011] Optionally, in some examples, including at least one preferred example, the sensed data may be received from a plurality of sensors. Technical benefits may include improved detection because the use of a plurality of sensors may detect acoustic waves from more than one location of the electrical energy storage system.

[0012] Optionally, in some examples, including at least one preferred example, the sensor in the electrical energy storage system may be at least one of a microphone, a horn filter connected to a waveguide, or an accelerometer.

[0013] According to a second aspect of the present disclosure, a computer-implemented method is provided, comprising: receiving, by a processing circuit of a computer, sensing data from at least one sensor arranged to detect acoustic waves emitted from an energy storage cell of an electrical energy storage system, the sensing data indicating at least one characteristic of the acoustic waves; applying, by the processing circuit, an algorithm configured to predict a thermal runaway event by analyzing the sensing data; and providing a message by the processing circuit if a result of the analysis is that thermal runaway is predicted.

[0014] A second aspect of the present disclosure may seek to improve detection of thermal runaway events in electrical energy storage systems. Technical benefits may include earlier detection, which provides more time and opportunity to take action in response to a predicted thermal runaway event.

[0015] Optionally, in some examples, including at least one preferred example, the algorithm is a machine learning model that is trained to predict thermal runaway events based on detecting acoustic waves generated by bubbles in an energy storage cell. Technical benefits may include improving the ability to detect thermal runaway events earlier and more accurately.

[0016] Optionally, in some examples, including at least one preferred example, the machine learning model is a supervised learning model that is trained on acoustic data from test cells to create a fingerprint library of characteristic sounds of thermal runaway events. Technical benefits may include improved models for predicting thermal runaway events.

[0017] Optionally, in some examples, including in at least one preferred example, the method may include: analyzing, by processing circuitry, acoustic waves at characteristic frequencies of electrolyte boiling prior to a thermal runaway event. For example, the processing circuitry may be configured to analyze acoustic waves at frequencies below 5 kHz (such as in the range of 1-2 kHz, or below 500 Hz) to predict a thermal runaway event. Technical benefits may include the ability to detect acoustic waves specifically generated by bubbles in an energy storage cell. Thus, the algorithm may target the frequencies most relevant to predicting a thermal runaway event by detecting bubbles.

[0018] Optionally, in some examples, including at least one preferred example, the method may include: wirelessly receiving, by the processing circuit, sensing data from a transmitter connected to the sensor. Technical benefits may include less complex integration due to reduced or eliminated use of hard wires.

[0019] Optionally, in some examples, including at least one preferred example, the sensing data may be received from a plurality of sensors configured to transmit the sensing data to the processing circuit. The sensors each detect sound waves and convert them into electrical signals. The sensors may be configured to detect infrasound.

[0020] Optionally, in some examples, including at least one preferred example, the sensor may be at least one of a microphone, a horn filter connected to a waveguide, or an accelerometer.Accelerometers provide a relatively cost-effective sensor solution.

[0021] There is also provided a computer program product comprising program code which, when executed by the processing circuit, performs the method of the second aspect.

[0022] There is also provided a non-transitory computer-readable storage medium comprising instructions which, when executed by the processing circuit, cause the processing circuit to perform the method of the second aspect.

[0023] According to a third aspect of the present invention, there is provided a system for detecting thermal runaway in an electrical energy storage system of a vehicle, the system comprising: a group of sensors arranged to detect sound waves emitted from energy storage cells of the electrical energy storage system, sensing data indicating at least one characteristic of the sound waves; a data collector configured to receive sensing signals from the sensors and transmit the sensing data to a processing circuit, the processing circuit configured to apply an algorithm, the algorithm configured to predict a thermal runaway event by analyzing the sensing data; and a vehicle processing circuit configured to provide a message if a result of the analysis is that thermal runaway is predicted.

[0024] A third aspect of the present disclosure may seek to improve detection of thermal runaway events in electrical energy storage systems. Technical benefits may include earlier detection, which provides more time and opportunity to take action in response to a predicted thermal runaway event.

[0025] Optionally, in some examples, including at least one preferred example, the system may include multiple sensor arrays in each energy storage pack of the energy storage system. Technical benefits may include more accurate detection of acoustic waves from multiple locations of the energy storage system, thereby improving prediction of thermal runaway events.

[0026] Optionally, in some examples, including at least one preferred example, the sensor can be a microphone arranged inside the housing of the energy storage system, the microphone being wirelessly connected to a data collector arranged outside the housing, or the sensor is a horn filter connected to a waveguide that guides sound waves to an air pressure sensor outside the housing, or an accelerometer.

[0027] There is also provided a vehicle comprising the system of the third aspect.

[0028] It will be appreciated by those skilled in the art that the disclosed aspects, examples (including any preferred examples) and / or the appended claims may be appropriately combined with each other. Additional features and advantages are disclosed in the following description, claims and drawings, and will in part be apparent to those skilled in the art or recognized by practicing the disclosure as described herein.

[0029] Also disclosed herein are computer systems, control units, code modules, computer-implemented methods, computer-readable media, and computer program products associated with the technical benefits discussed above. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is an exemplary system diagram of a computer system according to an example.

[0031] Figure 2The training process of the supervised learning model according to the example is schematically shown.

[0032] Figure 3A is a schematic side view of a system according to an example embodiment.

[0033] Figure 3B is a schematic top view of a system according to an example embodiment.

[0034] Figure 4A is a schematic side view of a system according to an example embodiment.

[0035] Figure 4B is a schematic top view of a system according to an example embodiment.

[0036] Figure 5 is a flow chart of method steps according to one example.

[0037] Figure 6 Based on the example Figure 1 Another view of .

[0038] Figure 7 is a flow chart of an exemplary method according to an example.

[0039] Figure 8 is a schematic diagram of an exemplary computer system for implementing the examples disclosed herein, according to an example. DETAILED DESCRIPTION

[0040] The detailed description set forth below provides information and examples of the disclosed technology in sufficient detail to enable those skilled in the art to practice the disclosure.

[0041] During a thermal runaway event in an electrical energy storage device such as a battery, the temperature of the battery's cells may exceed 1000°C. In addition, large amounts of flammable and hazardous gases are typically released. The heat generated in one cell during a thermal runaway event may trigger thermal runaway events in surrounding cells of the battery, resulting in thermal runaway propagation, which may cause serious consequences such as damage and injury. Although thermal runaway events can be detected using, for example, temperature sensors, the detection may be too late and an escalating thermal runaway may have already begun. Therefore, thermal runaway events need to be detected or predicted as early as possible so that preventive measures can be taken as soon as possible to reduce the risk of escalating thermal runaway escalation.

[0042] In order to solve the above problems, the inventors realized that it is necessary to measure the pressure or sound waves generated in the battery cells of the electric energy storage system, as will be explained in more detail below.

[0043] Figure 1 is an exemplary system diagram of a computer system 100 including a processing circuit 102 .

[0044] The processing circuit 102 is configured to receive sensing data D from at least one sensor 104, the at least one sensor being arranged to detect acoustic waves emanating from the electrical energy storage cells 106 of the electrical energy storage system 108. The sensing data D indicates at least one characteristic of the acoustic waves. The data D is transmitted to the processing circuit 102 via an optional transmitter 116.

[0045] The electrical energy storage system 108 may be arranged as a propulsion electrical energy storage system providing propulsion energy to a vehicle 109. Thus, the vehicle may be an electric, hybrid or plug-in hybrid vehicle comprising an electric engine, wherein the electrical energy storage system provides power to the electric engine. Furthermore, the present invention may also be applicable to stationary applications, marine applications.

[0046] The electrical energy storage system includes a plurality of battery cells 106 arranged in series and parallel as is known in the art.

[0047] Embodiments of the present disclosure are applicable to any type of electrical energy storage system, ie, batteries having liquid type electrolytes, such as lithium ion, lead acid, etc.

[0048] The processing circuit 102 is configured to apply an algorithm 110 configured to predict a thermal runaway event by analyzing the sensed data D. The sensed data D may include time domain data of the acoustic wave, from which various properties may be derived, including amplitude and frequency, as well as phase information and its variation over time, all of which may be characteristics of the acoustic wave.

[0049] The processing circuit 102 is further configured to provide a message W if the result of the analysis is that thermal runaway is predicted. The electronic message W may be provided to a control unit 112 of, for example, a vehicle or stationary application. The message W may provide instructions for the control unit 112 to initiate cooling of the battery cell 106, or control a switch circuit to disconnect a module or battery cell 106, or take other actions to prevent thermal runaway, and / or transmit a message to a passenger via a user interface 114, such as leaving the vehicle. The user interface 114 of the vehicle may be an audio output device, a display, or other visual indicator.

[0050] The characteristic of the acoustic wave may be at least one of the spectrum, amplitude, and phase of the acoustic wave. Generally speaking, any feature that forms a fingerprint of the acoustic wave may be used in an algorithm to identify an impending thermal event.

[0051] The acoustic waves 113 detected by the sensor 104 are generated by the bubbles 107 in the energy storage cell 106. The acoustic waves are caused by bubble vibration, rise, rupture, coalescence, bubble collision and implosion, and bubble resonance. When the cell approaches a thermal runaway event, the properties of the bubbles in the cell 106 also change due to changes in the material properties inside the cell 106. In other words, due to the change in material properties, the acoustic propagation inside the cell 106 also changes.

[0052] Therefore, the inventors realized that a series of events occur in a liquid energy storage cell before reaching thermal runaway, including electrolyte evaporation and gas generation. These events produce bubbles 107, which produce pressure / sound waves 113 including different frequency ranges. However, the early stages are dominated by low-frequency events or infrasound.

[0053] One of the sources of sound is the so-called Minnaert resonance, a phenomenon associated with bubbles in a liquid pulsating at their natural frequency. Technically, the frequency f of the bubbles inside the liquid is calculated as follows:

[0054]

[0055] Where a is the radius of the bubble, For variable efficiency, is the pressure inside the bubble, and is the difference between the density of water and the bulk density of the gas bubble. =1200 , the equation becomes So, for example, a bubble of the order of 10 mm would emit a frequency of about 200 Hz. Larger bubbles can produce even smaller frequencies, perhaps about 52 Hz for a 50 mm bubble.

[0056] As a sound wave travels, its energy is slowly lost as heat as the molecules of the medium through which the sound wave travels bump into each other as they transfer the sound wave's energy. The rate at which a sound wave is absorbed by a barrier depends on its frequency. If the width of the barrier is greater than the wavelength of the sound wave, the sound wave will be absorbed. As a simple example, a sine wave at 20 Hz has a wavelength of 17 meters and will therefore pass through most obstacles.

[0057] For example, a bubble in salt water with a wave frequency of 500 Hz has a wavelength of 3.12 meters. This wavelength will allow it to pass through existing obstacles in the energy storage system. For the size of most energy storage systems 108, battery cells 106, and surrounding components, sensors 104 can detect bubbles with a frequency of 5 kHz and a diameter of 100 microns. In general, low frequency waves are able to travel long distances with little dissipation, which allows fewer sensors to be required per energy storage pack.

[0058] Therefore, one source of the sound waves could be the bubble Minervall resonance. In addition, another source could be the bursting or collapse of the bubbles, which would generate sound waves in the 0.5-5 kHz range.

[0059] The processing circuit 102 is preferably further configured to predict a thermal runaway event by analyzing acoustic waves at a characteristic frequency of electrolyte boiling prior to the thermal runaway event. The frequency may be below 5 kHz, such as in the range of 100 Hz-2 kHz, or in the range of 1 kHz to 2 kHz, or below 500 Hz.

[0060] Preferably, the algorithm 110 is a machine learning model that is trained to predict thermal runaway events based on detecting acoustic waves generated by bubbles in the energy storage cell. Such a machine learning model may be a supervised learning model 110 that is trained on acoustic data from a test cell to create a fingerprint library of characteristic sounds of thermal runaway events.

[0061] In some possible embodiments, the computer system 100 is remote from the electrical energy storage system 100. The processing circuit 102 may be part of a cloud-based system arranged on a server, for example. Therefore, the processing circuit 102 is configured to wirelessly receive the sensing data D from the transmitter 116 connected to the sensor 104. The transmission technology may be, for example, Wifi, or any other available telecommunication technology, such as a mobile network.

[0062] Figure 2 The training process of the supervised learning model 110 is schematically shown. In a controlled environment (such as a laboratory), multiple records 201 (such as hundreds or thousands or more) or sound waves generated by multiple test cells 202 before a thermal runaway event occurs are made. These records are marked as belonging to a thermal runaway event and are fed to the supervised learning model 110, which creates a fingerprint library of characteristic sounds before the thermal runaway event (i.e., a few minutes before the thermal runaway event). Therefore, the supervised model 110 is taught to classify new data as belonging to a thermal runaway event in the near future. The supervised model 110 is then evaluated and tested on a verification cell set 204.

[0063] Supervised learning algorithms are often advantageously used in applications where labeled training data is available. For the present disclosure, labeled records can be obtained from previous records, where data from the record library is labeled as a thermal runaway event or not a thermal runaway event.

[0064] Figure 3A is a schematic side view of a system 300 for detecting thermal runaway in an electrical energy storage system 108 for a vehicle 109 or stationary application, and Figure 3BThe energy storage system 108 includes a plurality of energy storage cells 106 distributed on more than one energy storage pack 111 .

[0065] A set of sensors 302 is arranged to detect acoustic waves emitted from the energy storage cells 106 of the energy storage system 108. As described above, the sensed data D indicates at least one characteristic of the acoustic waves. A greater number of sensors is more advantageous in providing a higher signal-to-noise ratio.

[0066] According to an exemplary embodiment, the sensors 302 are represented here by an array of microphones 302 or accelerometers connected to a data collector 306 or transmitter.

[0067] The microphone 302 detects pressure / sound waves generated outside the battery cell 106 but in the battery cell 106. The microphone 302 converts the detected waves into electrical pulses / signals and transmits the electrical signals to the transmitter 306 via hard wire or via wireless communication (such as Bluetooth, Wi-Fi, etc.). The transmitter 306 sends the data D to the computer system 100, where the processing circuit 102 is configured to apply the algorithm 110 to predict thermal runaway events by analyzing the sensed data.

[0068] If the result of the analysis performed by the processing circuit 102 is that thermal runaway is predicted, the vehicle processing circuit 112 is configured to provide a message. The processing circuit may also be a fixed application processing circuit. The processing circuit 112 receives a message W with an instruction that thermal runaway is predicted from the processing circuit 102, so that in response, the processing circuit 112 may provide a warning message M or an instruction I to perform preventive measures, for example, by a cooling system or a switching circuit of the electrical energy storage system 108. Using the analysis proposed herein, a warning message M or an instruction I may be provided 15 minutes before a thermal runaway event.

[0069] Preferably, a plurality of sensor arrays 302 are arranged in each energy storage pack of the energy storage system 108. The sensor 302 may be arranged inside the housing 308 of the energy storage system 108, and located on the battery cell 106. In other words, the sensor 302 may be integrated into the energy storage pack 111.

[0070] In this system 300, the sensor is a microphone 302, which is arranged inside the housing 308 of the energy storage system 108 and is preferably wirelessly 309 connected to a data collector 306 arranged outside the housing 308. That is, the microphone 302 can be integrated into the energy storage package 111. However, as indicated, the microphone 302a can also be placed on the outer outer surface 320 of the housing 308, and thus not integrated inside the housing 308.

[0071] In some embodiments, the sensor may be an accelerometer. The accelerometer may measure the structural vibrations of the battery cell caused by the bubbles inside the energy storage pack 111. The analysis follows the method used when the sensor is a microphone.

[0072] The choice of accelerometer or microphone may depend on, for example, the available space within or on the surface of the energy storage pack.

[0073] Figure 4A is a schematic side view of a system 400 for detecting thermal runaway in an electrical energy storage system 108, and Figure 4B It is a schematic top view.

[0074] In this embodiment, the sensor may be a receiver 402 that includes a horn-shaped filter connected to a waveguide 404. In addition, the receiver 402 may include an amplifier that amplifies the received sound before transmitting it to a data collector 406, which here is an air pressure sensor 406 located at the other end of the waveguide 404. The air pressure sensor 406 converts the detected and amplified sound waves into electrical pulses. Next, the data from the air pressure sensor 406 is transmitted to the processing circuit 102 of the computer system 100, which is configured to apply an algorithm 110 configured to predict a thermal runaway event by analyzing the sensed data.

[0075] The waveguide 404 in the form of a pipe is useful for filtering out high frequency sound waves.

[0076] The receiver 402 may be disposed inside the housing 308 , or the receiver 402 a may be disposed on the outer surface 320 of the housing 308 .

[0077] Each energy storage pack 111 may include a dedicated air pressure sensor or a global air pressure sensor may be used for multiple energy storage packs 111. The air pressure sensor may be an infrasound sensor, i.e., a pressure wave sensor suitable for detecting low frequency sounds (such as below 5 kHz, below 1 kHz, below 500 Hz, or even below 100 Hz, or below 50 Hz).

[0078] Figure 5 is a flow chart of method steps according to an embodiment of the present disclosure.

[0079] In step S102, sensing data D from at least one sensor 104 is received by the processing circuit 102 of the computer system 100, the at least one sensor being arranged to detect acoustic waves emitted from the energy storage cell 106 of the energy storage system, the sensing data indicating at least one characteristic of the acoustic waves. In other words, the acoustic waves generated in the energy storage cell 106 due to the bubble dynamics in the fluid of the cell 106 are received by the sensor 104, and the data thereof is transmitted to the processing circuit 102.

[0080] In step S104, an algorithm 110 is applied by the processing circuit 102, the algorithm being configured to predict a thermal runaway event by analyzing the sensed data. Preferably, the algorithm is a machine learning model that is trained to predict a thermal runaway event based on detecting acoustic waves generated by bubbles in the energy storage cell. Preferably, the machine learning model may be a supervised learning model that is trained on acoustic data from a test cell to create a fingerprint library of characteristic sounds of a thermal runaway event.

[0081] In step S106 , if the result of the analysis is that thermal runaway is predicted, a warning message is provided by the processing circuit 102 .

[0082] In order to filter out acoustic dynamics irrelevant to thermal runaway event prediction from the bubble dynamics, analysis may be performed on acoustic waves at characteristic frequencies of electrolyte boiling prior to a thermal runaway event. For example, such frequencies may be below 5 kHz, such as in the range of 1-2 kHz or 20 Hz to 500 Hz to predict a thermal runaway event.

[0083] Figure 6 Based on the example Figure 1 Another view of . Figure 6 A computer system 100 is shown, which includes a processing circuit 102, which is configured to: receive sensing data D from at least one sensor 104, wherein the at least one sensor is arranged to detect sound waves emitted from an energy storage cell 106 of an energy storage system 108, and the sensing data D is indicative of at least one characteristic of the sound waves.

[0084] The processing circuit 102 is configured to apply an algorithm 110 configured to predict a thermal runaway event by analyzing the sensed data D and to provide a warning message W if a thermal runaway is predicted as a result of the analysis.

[0085] Figure 7 is a flow chart of a method according to an example.

[0086] In step S202, sensing data from at least one sensor is received by a processing circuit of a computer system, wherein the at least one sensor is arranged to detect sound waves emitted from an energy storage cell of an energy storage system, and the sensing data indicates at least one characteristic of the sound waves.

[0087] In step S204 , an algorithm is applied by the processing circuit, the algorithm being configured to predict a thermal runaway event by analyzing the sensed data.

[0088] In step S206 , if the result of the analysis is that thermal runaway is predicted, a warning message is provided by the processing circuit.

[0089] Figure 8 800 is a schematic diagram of a computing system 800 for implementing the examples disclosed herein. The computer system 800 is suitable for executing instructions from a computer-readable medium to perform these and / or any functions or processes described herein. The computer system 800 may be connected (e.g., networked) to other machines in a LAN, an intranet, an extranet, or the Internet. Although only a single device is shown, the computer system 800 may include any device collection that executes an instruction set (or multiple instruction sets) individually or jointly to perform any one or more of the methods discussed herein. Therefore, any reference to a computer system, a computing system, a computer device, a computing device, a control system, a control unit, an electronic control unit (ECU), a processor device, a processing circuit, etc. in the present disclosure and / or claims includes a reference to one or more such devices to execute an instruction set (or multiple instruction sets) individually or jointly to perform any one or more of the methods discussed herein. For example, the control system may include a single control unit or multiple control units connected to each other or otherwise communicatively coupled, so that any executed function can be distributed between the control units as needed. In addition, such devices can communicate with each other or with other devices through various system architectures (such as directly or via a controller area network (CAN) bus, etc.).

[0090] The computer system 800 may include at least one computing device or electronic device that can include firmware, hardware and / or execute software instructions to implement the functionality described herein. The computer system 800 may include a processing circuit 802 (e.g., a processing circuit including one or more processor devices or control units), a memory 804, and a system bus 806. The computer system 800 may include at least one computing device having a processing circuit 802. The system bus 806 provides an interface for system components including, but not limited to, the memory 804 and the processing circuit 802. The processing circuit 802 may include any number of hardware components for performing data or signal processing or for executing computer code stored in the memory 804. The processing circuit 802 may include, for example, a general-purpose processor, a special-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a circuit containing a processing component, a group of distributed processing components, a group of distributed computers configured for processing, or other programmable logic devices designed to perform the functions described herein, discrete gate or transistor logic, discrete hardware components, or any combination thereof. The processing circuit 802 may also include computer executable code that controls the operation of the programmable device.

[0091] The system bus 806 can be any of several types of bus structures, which can be further interconnected to a memory bus (with or without a memory controller), a peripheral bus, and / or a local bus using any of a variety of bus architectures. The memory 804 can be one or more devices for storing data and / or computer code to complete or facilitate the methods described herein. The memory 804 can include a database component, an object code component, a script component, or other types of information structures for supporting various activities herein. Any distributed or local memory device can be utilized with the systems and methods of the present specification. The memory 804 can be communicatively connected to the processing circuit 802 (e.g., via a circuit or any other wired, wireless, or network connection) and can include computer code for performing one or more processes described herein. The memory 804 may include nonvolatile memory 808 (e.g., read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.) and volatile memory 810 (e.g., random access memory (RAM)), or any other medium that can be used to carry or store desired program code in the form of machine-executable instructions or data structures and that can be accessed by a computer or other machine having the processing circuit 802. A basic input / output system (BIOS) 812 may be stored in the nonvolatile memory 808 and may include the basic routines that help to transfer information between elements within the computer system 800.

[0092] The computer system 800 may also include or be coupled to non-transitory computer-readable storage media such as storage device 814, which may include, for example, an internal or external hard disk drive (HDD) (e.g., enhanced integrated drive electronics (EIDE) or serial advanced technology attachment (SATA)), a HDD for storage (e.g., EIDE or SATA), flash memory, etc. The storage device 814 and other drives associated with computer-readable and computer-usable media may provide non-volatile storage of data, data structures, computer-executable instructions, etc.

[0093] The hard-coded or soft-coded computer code may be provided in the form of one or more modules. The module may be implemented as software and / or hard-coded in the circuit to implement the functionality described herein in whole or in part. These modules may be stored in a storage device 814 and / or a volatile memory 810 that may include an operating system 816 and / or one or more program modules 818. All or part of the examples disclosed herein may be implemented as a computer program 820 stored on a temporary or non-temporary computer-available or computer-readable storage medium (e.g., a single medium or multiple media) such as a storage device 814, which includes complex programming instructions (e.g., complex computer-readable program code) that cause the processing circuit 802 to perform the actions described herein. Therefore, the computer-readable program code of the computer program 820 may include software instructions for implementing the functionality of the examples described herein when executed by the processing circuit 802. In some examples, storage device 814 may be a computer program product (e.g., a readable storage medium) having computer program 820 stored thereon, wherein at least a portion of computer program 820 may be loadable (e.g., loaded into a processor) for implementing the functionality of the examples described herein when executed by processing circuit 802. Processing circuit 802 may serve as a controller or control system of computer system 800 for implementing the functionality described herein.

[0094] The computer system 800 may include an input device interface 822 configured to receive input and selections to be transmitted to the computer system 800 when executing instructions, such as from a keyboard, mouse, touch-sensitive surface, etc. Such input devices can be connected to the processing circuit 802 through an input device interface 822 coupled to the system bus 806, but can be connected through other interfaces (such as a parallel port, an Institute of Electrical and Electronics Engineers (IEEE) 1394 serial port, a universal serial bus (USB) port, an IR interface, etc.). The computer system 800 may include an output device interface 824, which is configured to forward output to a display, a video display unit (e.g., a liquid crystal display (LCD) or a cathode ray tube (CRT)). The computer system 800 may include a communication interface 826 suitable for communicating with a network as appropriate or as needed.

[0095] The operational actions described in any of the exemplary aspects of this article are described to provide examples and discussions. These actions can be performed by hardware components, can be embodied in machine executable instructions so that a processor performs these actions, or can be performed by a combination of hardware and software. Although a specific order of method actions can be shown or described, the order of actions can be different. In addition, two or more actions can be performed simultaneously or partially simultaneously.

[0096] Example 1: A computer system comprising a processing circuit configured to: receive sensing data from at least one sensor arranged to detect acoustic waves emanating from an energy storage cell of an electrical energy storage system, the sensing data indicating at least one characteristic of the acoustic waves; apply an algorithm configured to predict a thermal runaway event by analyzing the sensing data; and provide a message if a result of the analysis is that thermal runaway is predicted.

[0097] Example 2: A computer system according to Example 1, wherein the algorithm is a machine learning model that is trained to predict thermal runaway events based on detecting sound waves generated by bubbles in energy storage cells.

[0098] Example 3: According to the computer system of Example 2, the machine learning model is a supervised learning model, which is trained on acoustic data from test cells to create a fingerprint library of characteristic sounds of thermal runaway events.

[0099] Example 4: The computer system of any one of Examples 1 to 3, wherein the processing circuit is further configured to: predict a thermal runaway event by analyzing acoustic waves at a characteristic frequency of electrolyte boiling prior to the thermal runaway event.

[0100] Example 5: The computer system of any of Examples 1 to 4, wherein the processing circuit is configured to wirelessly receive the sensing data from a transmitter connected to the sensor.

[0101] Example 6: The computer system of any one of Examples 1 to 5, wherein the sensory data is received from a plurality of sensors.

[0102] Example 7: The computer system of any of Examples 1 to 6, wherein the sensor in the electrical energy storage system is at least one of a microphone, a horn filter connected to a waveguide, or an accelerometer.

[0103] Example 8: A computer-implemented method comprising:

[0104] Receiving, by a processing circuit of a computer, sensing data from at least one sensor arranged to detect acoustic waves emanating from an energy storage cell of an electrical energy storage system, the sensing data indicating at least one characteristic of the acoustic waves; applying, by the processing circuit, an algorithm configured to predict a thermal runaway event by analyzing the sensing data; and providing, by the processing circuit, a message if a result of the analysis is that thermal runaway is predicted.

[0105] Example 9: The computer-implemented method of Example 8, wherein the algorithm is a machine learning model trained to predict thermal runaway events based on detecting acoustic waves generated by gas bubbles in an electrical energy storage cell.

[0106] Example 10: According to the computer-implemented method of Example 9, the machine learning model is a supervised learning model, which is trained on acoustic data from test cells to create a fingerprint library of characteristic sounds of thermal runaway events.

[0107] Example 11: The computer-implemented method of any one of Examples 8 to 10, comprising: predicting a thermal runaway event by analyzing, by processing circuitry, acoustic waves at a characteristic frequency of electrolyte boiling prior to the thermal runaway event.

[0108] Example 12: A computer-implemented method according to any one of Examples 8 to 11, comprising:

[0109] The sensed data is wirelessly received by the processing circuit from a transmitter connected to the sensor.

[0110] Example 13: The computer-implemented method of any of Examples 8 to 12, wherein the sensed data is received from a plurality of sensors configured to transmit the sensed data to the processing circuit.

[0111] Example 14: The computer-implemented method of any of Examples 8 to 13, wherein the sensor in the electrical energy storage system is at least one of a microphone, a horn filter connected to a waveguide, or an accelerometer.

[0112] Example 15: A computer program product comprising program code for performing the method according to any one of Examples 8 to 14 when executed by a processing circuit.

[0113] Example 16: A non-transitory computer-readable storage medium comprising instructions that, when executed by the processing circuit, cause the processing circuit to perform the method according to any one of Examples 8 to 14.

[0114] Example 17: A system for detecting thermal runaway in an electrical energy storage system of a vehicle, the system comprising: a group of sensors arranged to detect sound waves emitted from energy storage cells of the electrical energy storage system, the sensing data indicating at least one characteristic of the sound waves; a data collector configured to receive sensing signals from the sensors and transmit the sensing data to a processing circuit, the processing circuit configured to apply an algorithm configured to predict a thermal runaway event by analyzing the sensing data; and a vehicle processing circuit configured to provide a message if a result of the analysis is that thermal runaway is predicted.

[0115] Example 18: The system of Example 17, comprising a plurality of sensor arrays in each electrical energy storage pack of the electrical energy storage system.

[0116] Example 19: A system according to any of Examples 18 to 17, wherein the sensor is a microphone arranged inside the housing of the energy storage system, the microphone being wirelessly connected to a data collector arranged outside the housing, or the sensor is a horn filter connected to a waveguide that guides sound waves to an air pressure sensor outside the housing, or an accelerometer.

[0117] Example 20: A vehicle comprising a system according to any one of Examples 17 to 19.

[0118] The terms used herein are only for the purpose of describing specific aspects and are not intended to limit the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular forms "one", "a kind of" and "the" are intended to also include plural forms. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items. It should also be understood that the terms "include" and / or "comprising" when used herein indicate the presence of stated features, integers, actions, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, actions, steps, operations, elements, parts and / or their groups.

[0119] It should be understood that although the terms first, second, etc. can be used to describe various elements in this article, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, without departing from the scope of the present disclosure, the first element can be referred to as the second element, and similarly, the second element can be referred to as the first element.

[0120] Relative terms such as "below" or "above" or "upper" or "lower" or "horizontal" or "vertical" may be used herein to describe the relationship of one element to another element, as shown in the figures. It should be understood that these terms and those discussed above are intended to cover different device orientations in addition to the orientations depicted in the figures. It should be understood that when an element is referred to as being "connected" or "coupled" to another element, the element may be directly connected or directly coupled to the other element, or there may be intermediate elements. In contrast, when an element is referred to as being "directly connected to" or "directly coupled to" another element, there are no intermediate elements.

[0121] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those commonly understood by those skilled in the art to which the present disclosure belongs. It should also be understood that, unless otherwise clearly defined herein, the terms used herein should be interpreted as meanings consistent with their meanings in the context of this specification and the relevant art, and should not be interpreted in an idealized or overly formal sense.

[0122] It should be understood that the present disclosure is not limited to the aspects described above and shown in the accompanying drawings; rather, those skilled in the art will recognize that many changes and modifications may be made within the scope of the present disclosure and the appended claims. In the drawings and description, various aspects have been disclosed for illustrative purposes only and not for limiting purposes, and the scope of the present disclosure is set forth in the appended claims.

Claims

1. A computer system (100) comprising a processing circuit (102), the processing circuit being configured to: receiving sensed data (D) from at least one sensor (104), the at least one sensor being arranged to detect acoustic waves emanating from an electrical energy storage cell (106) of an electrical energy storage system (108), the sensed data being indicative of at least one characteristic of the acoustic waves, applying an algorithm (110) that predicts a thermal runaway event by analyzing the sensed data, If the result of the analysis is that thermal runaway is predicted, a message (W) is provided.

2. The computer system of claim 1 , wherein the algorithm is a machine learning model trained to predict thermal runaway events based on detecting acoustic waves (113) generated by gas bubbles (107) in the energy storage cell.

3. The computer system of claim 2, wherein the machine learning model is a supervised learning model that is trained on acoustic data from test cells to create a fingerprint library of characteristic sounds of thermal runaway events.

4. The computer system according to any one of claims 1 to 3, wherein the processing circuit is further configured to: The thermal runaway event is predicted by analyzing the acoustic waves at the characteristic frequencies of electrolyte boiling that precede the thermal runaway event.

5. The computer system of any one of claims 1 to 4, wherein the processing circuit is configured to receive the sensed data wirelessly from a transmitter (116) connected to the sensor.

6. The computer system of any one of claims 1 to 5, wherein the sensory data is received from a plurality of sensors (302, 402).

7. The computer system of any one of claims 1 to 6, wherein the sensor in the electrical energy storage system is at least one of a microphone, a horn filter connected to a waveguide, or an accelerometer.

8. A computer-implemented method comprising: receiving (S102, S202) by a processing circuit of a computer system sensing data from at least one sensor arranged to detect acoustic waves emanating from an electrical energy storage cell of an electrical energy storage system, the sensing data being indicative of at least one characteristic of the acoustic waves, applying (S104, S204) an algorithm by the processing circuit, the algorithm being configured to predict a thermal runaway event by analyzing the sensed data, If a result of the analysis is that thermal runaway is predicted, a warning message is provided ( S106 , S206 ) by the processing circuit.

9. The computer-implemented method of claim 8, wherein the algorithm is a machine learning model trained to predict thermal runaway events based on detecting acoustic waves generated by gas bubbles in an electrical energy storage cell.

10. The computer-implemented method of claim 9, wherein the machine learning model is a supervised learning model that is trained on acoustic data from test cells to create a fingerprint library of characteristic sounds of thermal runaway events.

11. A computer-implemented method according to any one of claims 8 to 10, comprising: Acoustic waves at a characteristic frequency of electrolyte boiling preceding a thermal runaway event are analyzed by the processing circuit.

12. A computer-implemented method according to any one of claims 8 to 11, comprising: The sensed data is wirelessly received by the processing circuit from a transmitter connected to the sensor.

13. A computer program product comprising program code which, when executed by a processing circuit, performs the method according to any one of claims 8 to 12.

14. A non-transitory computer-readable storage medium comprising instructions which, when executed by a processing circuit, cause the processing circuit to perform the method of any one of claims 8 to 12.

15. A system (300, 400) for detecting thermal runaway in an electrical energy storage system, the system comprising: a set of sensors (104, 302, 402) arranged to detect acoustic waves emanating from an electrical energy storage cell (106) of an electrical energy storage system, the sensed data being indicative of at least one characteristic of the acoustic waves; a data collector (306) configured to receive a sensing signal from the sensor and transmit the sensing data to a processing circuit, the processing circuit configured to apply an algorithm configured to predict a thermal runaway event by analyzing the sensing data; as well as Processing circuitry (112) is configured to provide a message if a result of the analysis is that thermal runaway is predicted.

Images