Intelligent control system of energy-saving double-drum washing machine

Abstract

The invention relates to the technical field of intelligent control of double-drum washing machines, and discloses an intelligent control system of an energy-saving double-drum washing machine, which comprises a hardware execution unit used for providing multi-mode sensing, accurate liquid management, mechanical execution and energy recovery functions; the control processing unit is used for processing the received data, operating an algorithm and coordinating the operation of each component of the system; the cooperative control software module runs on the main control board and comprises an acoustic fingerprint identification and fault diagnosis module and an intelligent fluid precise counterweight and cooling module; an AI-driven collaborative decision and adaptive optimization module; the invention discloses a micro heat pump energy recovery and precise temperature control linkage module. By means of the high-sensitivity acoustic array sensor and the acoustic fingerprint recognition and fault diagnosis module, clothes imbalance is recognized, point-to-point liquid balance weight is achieved by means of the micro-fluidic spraying valve array, the optimal dehydration cooperative scheduling strategy is generated, water and electricity resources are greatly saved, and the dehydration efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control of twin-drum washing machines, in particular to an intelligent control system for energy-saving twin-drum washing machines. Background Art

[0002] Household appliances, especially washing machines, play a vital role in modern household life. With growing consumer demand for energy conservation, efficiency, and intelligence, washing machine technology continues to evolve. Twin-tub washing machines, with their unique dual-zone washing capabilities and convenience in specific applications, are becoming a key market segment.

[0003] Existing twin-drum washing machines primarily perform washing and dehydration functions mechanically. Their control systems typically employ pre-set programs and control logic based on simple sensor feedback. During the dehydration process, the motor drives the washing drum to rotate at high speed. Centrifugal force forces the clothes to adhere to the drum wall, and water is removed.

[0004] However, in existing twin-drum washing machine technology, the uneven distribution of clothes during high-speed dehydration can easily cause violent vibrations and abnormal noises in the washing drum. The traditional solution is often to roughly stop the dehydration process and refill the entire washing drum with water. This method not only consumes a lot of water resources and electricity, but also prolongs the washing time. The existing system lacks the ability to accurately identify the source of vibration, making it difficult to distinguish between clothing entanglement and mechanical wear failures, making it difficult to implement targeted intervention. In addition, before high-temperature drainage, the cooling operation performed to meet safety requirements usually relies on high-energy mechanical stirring or large-flow drainage, which causes unnecessary waste of energy and water resources. Therefore, the present invention provides an intelligent control system for an energy-saving twin-drum washing machine to address the shortcomings of the prior art. Summary of the Invention

[0005] In view of the deficiencies in the prior art, the present invention provides an intelligent control system for an energy-saving twin-drum washing machine, which solves the deficiencies in dehydration stability control and high-temperature drainage temperature control of the prior art twin-drum washing machines.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0007] A first aspect of the present invention provides an intelligent control system for an energy-saving twin-tub washing machine, comprising a hardware execution unit, a control processing unit, and a collaborative control software module running on the control processing unit.

[0008] The hardware execution unit includes:

[0009] Clutch module: configured to receive a control signal and perform an engagement or disengagement operation of the washing tub.

[0010] Temperature sensor module: configured to detect the water temperature signal inside each washing tub in real time.

[0011] Water inlet control module and drainage control module: configured to receive control signals and adjust the flow of cold water entering each washing tub, as well as perform drainage operations.

[0012] Barrel collision detection module (vibration): configured to monitor the relative position, vibration state or deformation state of the barrels in real time and output a barrel collision risk signal.

[0013] High-sensitivity acoustic array sensor: Multiple miniature piezoelectric microphones or micro-electromechanical system microphones are installed on the outer wall of each washing drum, arranged in a ring or specific geometric layout, and configured to collect wide-band sound wave signals generated during the operation of the washing machine in real time.

[0014] Microfluidic spray valve array: A plurality of microfluid spray valves are integrated in the upper annular area of ​​each washing drum, and each valve is configured to independently control the flow direction and spray pattern of extremely small flow rates.

[0015] Micro heat pump energy recovery unit: integrated in the drainage path and configured to capture waste heat from high-temperature wastewater.

[0016] Thermal energy storage unit: arranged in conjunction with the micro heat pump energy recovery unit, and configured to store low-grade thermal energy recovered by the micro heat pump energy recovery unit.

[0017] Preheating unit: configured to utilize the energy in the thermal energy storage unit to preheat a small amount of newly injected cold water.

[0018] The control processing unit includes:

[0019] Main control board (with integrated AI chip): As a core component, it integrates an AI chip with computing capabilities and is configured to run the collaborative control software module, receive multi-source sensor data, and output control instructions.

[0020] Drive board: configured to receive motor instructions from the main control board and control the operating parameters of the washing machine motor, including speed, start and stop, and inching beat.

[0021] The collaborative control software module runs on the main control board, and its functional modules include:

[0022] Acoustic fingerprint recognition and fault diagnosis module: configured to receive the sound wave signals collected by the high-sensitivity acoustic array sensor, use the deep learning model to extract features and recognize patterns on the sound wave signals, and determine in real time the specific source and nature of the current vibration or abnormal noise, such as clothing imbalance, abnormal bearing noise, motor failure or minor collision, and output the diagnosis results.

[0023] Intelligent fluid precision balancing and cooling module: configured to receive the diagnosis results of the acoustic fingerprint recognition and fault diagnosis module, and control the microfluidic spray valve array to perform milliliter-level precise liquid balancing or layered directional spray cooling according to the diagnosis results.

[0024] AI-driven collaborative decision-making and adaptive optimization module: This module is configured to integrate, in real time, multiple modal data streams, including diagnostic results from the acoustic fingerprint recognition and fault diagnosis module, water temperature data from the temperature sensing module, signals from the barrel collision detection module (vibration), and motor operating parameters. Based on reinforcement learning or deep reinforcement learning algorithms, this module continuously learns and optimizes to autonomously generate a dehydration collaborative scheduling strategy and a water cooling temperature control strategy. The dehydration collaborative scheduling strategy includes timing, speed, clutch status, and preventive micro-weighting instructions for the intelligent fluid precision weighting and cooling module.

[0025] Micro heat pump energy recovery and precise temperature control linkage module: configured to cooperate with the drainage control module during the high-temperature drainage stage, capture part of the waste heat of the high-temperature wastewater and store it in the thermal energy storage unit, and when cold water needs to be injected for cooling or a specific washing mode requires warm water, the AI-driven collaborative decision-making and adaptive optimization module is scheduled to instruct the preheating unit to use the recovered heat energy to preheat the small amount of newly injected cold water.

[0026] Dehydration collaborative scheduling module: configured to generate instructions for coordinating the timing, speed and clutch status of multiple barrels of dehydration to optimize dehydration stability.

[0027] Water temperature dynamic adjustment module: configured to run cooling logic according to the water temperature signal of the temperature sensing module to achieve water temperature reduction.

[0028] The drum collision risk monitoring and avoidance module is configured to analyze drum collision risk signals in real time, assess the collision risk level, and generate avoidance instructions when potential risks are detected. These avoidance instructions include speed reduction and shutdown, quantitative water injection and cooling, clutch state switching, and high-frequency jitter beat imbalance treatment for faulty drums; as well as strategies to maintain operational efficiency for non-faulty drums. This drum collision risk monitoring and avoidance module is linked to the dehydration coordinated scheduling module.

[0029] A second aspect of the present invention provides an intelligent control method for an energy-saving twin-tub washing machine, which is applied to the intelligent control system of the energy-saving twin-tub washing machine described in the first aspect of the present invention. The method comprises the following steps:

[0030] S1: Water temperature detection and cooling logic execution: The temperature sensing module in the system detects the water temperature inside each washing tub in real time. If the water temperature exceeds the preset safety threshold, the main control board (with integrated AI chip) executes the cooling logic through the water temperature dynamic adjustment module and the AI-driven collaborative decision-making and adaptive optimization module. Specifically:

[0031] The drainage control module closes the drainage valve;

[0032] The water inlet control module and the microfluidic spray valve array work together to inject cold water to the preset cooling water level based on the decisions of the AI-driven collaborative decision-making and adaptive optimization module. The intelligent fluid precision weighting and cooling module precisely sprays cold water in a layered and directional spray mode, keeping the impeller stationary and utilizing the natural sedimentation of the water density gradient to form a low-temperature layer at the bottom.

[0033] When the temperature sensing module detects that the bottom temperature is less than or equal to a first threshold, the AI-driven collaborative decision-making and adaptive optimization module synchronously instructs the drainage control module to open the drainage valve and continuously instructs the water inlet control module to inject cold water for injection and drainage collaborative heat exchange. When the water temperature is continuously less than or equal to a second threshold, water injection is stopped, and the first threshold is greater than the second threshold;

[0034] If the temperature condition is not met within the preset time, the AI-driven collaborative decision-making and adaptive optimization module forces the water inlet valve to remain open and continue to inject water until the preset high temperature threshold is reached, and then opens the drain valve;

[0035] When the bottom temperature continuously reaches the target temperature threshold and stabilizes for a certain period of time, the water inlet is stopped and the drainage control module is instructed to drain all the water in the barrel.

[0036] S2: Dehydration command is sent and the coordinated dehydration state is entered: when the water temperature in the barrel reaches the safety threshold and the water in the barrel is completely emptied, the main control board (with integrated AI chip) sends a dehydration command and the system enters the coordinated dehydration state.

[0037] S3: Continuous monitoring and dynamic adjustment of operating status: During the collaborative dehydration process, the system continuously monitors the operating status of the washing drum, including vibration and abnormal noise. The acoustic fingerprint recognition and fault diagnosis module (AFDDM) receives the original sound wave signal collected by the high-sensitivity acoustic array sensor, uses a deep learning model to perform feature extraction and pattern recognition, and determines the specific source and nature of the current vibration or abnormal noise in real time. The AI-driven collaborative decision-making and adaptive optimization module dynamically adjusts the monitoring sensitivity of the barrel collision detection module (vibration) based on the results of the acoustic fingerprint recognition and fault diagnosis module and the signal of the barrel collision detection module (vibration).

[0038] S4: Generation and execution of optimal dehydration collaborative scheduling strategy: The AI-driven collaborative decision-making and adaptive optimization module analyzes the diagnostic results of the acoustic fingerprint recognition and fault diagnosis module, the signal of the barrel collision detection module (vibration), and the motor operating parameters in real time, dynamically generates the optimal dehydration collaborative scheduling strategy, and instructs the drive board and clutch module to execute it. The strategy includes:

[0039] The AI-driven collaborative decision-making and adaptive optimization module outputs a collaborative signal to the drive board through the dehydration collaborative scheduling module. The drive board controls the clutch module to switch to the dehydration state and triggers a low-frequency micro-motion beat to ensure engagement.

[0040] The first tub (the tub that starts dehydration first) is controlled to execute a stepped accelerated dehydration curve.

[0041] If the acoustic fingerprint recognition and fault diagnosis module identifies that any barrel has a slight imbalance tendency, the AI-driven collaborative decision-making and adaptive optimization module instructs the intelligent fluid precision balancing and cooling module to perform preventive micro-liquid balancing.

[0042] If the second bucket needs to perform a drainage operation when the first bucket is dehydrating at a high speed, the AI-driven collaborative decision-making and adaptive optimization module instructs the second bucket to suspend drainage and use it as a static counterweight to suppress superimposed disturbances.

[0043] After the first barrel is dehydrated, the AI-driven collaborative decision-making and adaptive optimization module instructs the second barrel to perform high-speed dehydration. When the second barrel is dehydrating, if an imbalance tendency is detected, the current dehydration state is maintained, and the next stage of water filling is performed on the first barrel to use it as a counterweight. After the water filling is completed, the second barrel continues to perform step-by-step accelerated dehydration.

[0044] S5: Barrel Crash Risk Assessment and Chain Response Avoidance: The system determines whether there is a barrel crash risk. If the barrel crash detection module sends a barrel crash signal or the high-sensitivity acoustic array sensor captures the unique acoustic fingerprint of the barrel crash, the acoustic fingerprint recognition and fault diagnosis module accurately diagnoses the specific cause of the barrel crash. The AI-driven collaborative decision-making and adaptive optimization module executes chain response avoidance instructions through the barrel crash risk monitoring and avoidance module based on the diagnosis results of the acoustic fingerprint recognition and fault diagnosis module:

[0045] The faulty washing tub is controlled to slow down to a stop, the intelligent fluid precise weight balancing and cooling module is instructed to inject a precise amount of water for cooling, the clutch module is switched to the washing state, the drive board performs unbalance processing on the faulty washing tub, and outputs a high-frequency jitter beat.

[0046] At the same time, based on the current status of the non-faulty washing drum, the AI-driven collaborative decision-making and adaptive optimization module maximizes its operating efficiency to avoid unnecessary downtime or interruption.

[0047] When the clutch module switches state, the drive plate triggers a low-frequency micro-motion beat to ensure engagement accuracy.

[0048] S6: End of washing cycle: After dehydration is completed, the current washing cycle ends.

[0049] The present invention provides an intelligent control system for an energy-saving twin-drum washing machine. It has the following beneficial effects:

[0050] 1. By introducing a highly sensitive acoustic array sensor and an acoustic fingerprint recognition and fault diagnosis module, the present invention can perform root-cause diagnosis of vibrations or abnormal noises generated during the operation of the washing drum, accurately identifying specific sources such as clothing imbalance and mechanical failures. Utilizing a microfluidic spray valve array, the present invention achieves point-to-point liquid balancing at the milliliter level. Reinforcement learning is used to autonomously generate an optimal dehydration coordination scheduling strategy. Combined with the chain response of the drum collision risk monitoring and avoidance module, the present invention only performs speed reduction, quantitative water injection cooling, and high-frequency jitter correction on the faulty washing drum, significantly saving water and electricity resources and improving dehydration efficiency.

[0051] 2. This invention utilizes the intelligent fluid precise weighting and the layered directional spray mode of the cooling module to precisely spray cold water to the junction of the high-temperature water and cold water layers, and achieves heat transfer by natural sedimentation of the water body's density gradient. No impeller stirring is required throughout the process, completely eliminating the energy consumption required for traditional stirring and cooling. At the same time, combined with dual-threshold linkage control and injection and discharge coordination mechanism, this closed-loop management of energy recovery and reuse further improves the overall energy efficiency of the system.

[0052] 3. The present invention adopts an AI-driven collaborative decision-making and adaptive optimization module as the core intelligent engine. Based on reinforcement learning or deep reinforcement learning algorithms, it can integrate multiple information such as the diagnosis results from the acoustic fingerprint recognition and fault diagnosis module, the water temperature data from the temperature sensor module, and the displacement deformation data from the barrel collision detection module in real time, thereby significantly improving the dehydration stability of the entire machine and effectively reducing the risk of barrel collision. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 This is a diagram of the intelligent control system architecture of an energy-saving twin-tub washing machine of the present invention;

[0054] Figure 2 Schematic diagram of the hardware execution unit of the present invention;

[0055] Figure 3 Schematic diagram of the control processing unit of the present invention;

[0056] Figure 4 Schematic diagram of the collaborative control software module of the present invention;

[0057] Figure 5 This is a flow chart of an intelligent control method for an energy-saving twin-drum washing machine of the present invention. DETAILED DESCRIPTION

[0058] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the present specification. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0059] Please see the attached Figure 1 , Figure 1 This is an architecture diagram of an intelligent control system for an energy-saving twin-tub washing machine according to one embodiment of the present invention. The embodiment of the present invention provides an intelligent control system for an energy-saving twin-tub washing machine, including a hardware execution unit, a control processing unit, and a collaborative control software module:

[0060] The hardware execution unit provides multimodal sensing, precise liquid management, mechanical execution, and energy recovery. It includes a clutch module, temperature sensor module, water inlet control module, water outlet control module, barrel collision detection module, high-sensitivity acoustic array sensor, microfluidic spray valve array, micro heat pump energy recovery unit, thermal energy storage unit, and preheating unit.

[0061] The control processing unit processes received data, runs algorithms, and coordinates the operation of various system components. It comprises a core main control board and a driver board that transmits motor commands. The main control board receives various sensor data from the hardware execution units, runs the coordinated control software modules, and outputs control commands to the driver board and other hardware execution modules. The driver board converts the main control board's control commands into signals that the motor can recognize, precisely controlling the operation of the washing machine's motor.

[0062] The collaborative control software module runs on the main control board and is used to implement intelligent control and optimization of the system. It includes an acoustic fingerprint recognition and fault diagnosis module, an intelligent fluid precision weighting and cooling module, an AI-driven collaborative decision-making and adaptive optimization module, a micro-heat pump energy recovery and precise temperature control linkage module, a dehydration collaborative scheduling module, a dynamic water temperature adjustment module, and a barrel collision risk monitoring and avoidance module. These software modules exchange data and coordinate logic to achieve precise control of the hardware execution units.

[0063] The system's operating principle involves the integration of multi-source data and real-time decision-making. For example, the AI-driven collaborative decision-making and adaptive optimization module integrates, in real time, diagnostic results from the acoustic fingerprint recognition and fault diagnosis module, water temperature data from the temperature sensor module, signals from the barrel collision detection module, and motor operating parameters. Based on these inputs, the AI-driven collaborative decision-making and adaptive optimization module generates the optimal dehydration collaborative scheduling strategy and water cooling temperature control strategy according to a preset or trained optimization model. The input data can be expressed as:

[0064] Input={D AFDDM ,T water ,S impact ,P motor};

[0065] The output strategy can be expressed as:

[0066] Output={S dewater ,S temp＿control};

[0067] In the formula, Input is input data; Output is output strategy; D AFDDM Represents the diagnostic result output by the acoustic fingerprint recognition and fault diagnosis module. Its value can be a specific fault type such as clothing imbalance, bearing noise, motor failure, or minor collision; T water Indicates the water temperature in the barrel measured in real time by the temperature sensor module; S impact P represents the barrel collision risk signal output by the barrel collision detection module, and its value can be a value indicating the vibration amplitude or the degree of barrel deformation; motor Indicates motor operating parameters, such as motor speed (RPM), current (A), etc.; Sdewater It represents the dehydration collaborative scheduling strategy generated by the AI-driven collaborative decision-making and adaptive optimization module, including but not limited to dehydration timing, speed, clutch status, and preventive micro-weighting instructions of the intelligent fluid precision weighting and cooling module. temp＿control This indicates the water-cooling temperature control strategy generated by the AI-driven collaborative decision-making and adaptive optimization module. This strategy includes, but is not limited to, water inlet flow rate, spray pattern, and drainage timing.

[0068] Please see the attached Figure 2 , Figure 2 This is a schematic diagram of a hardware execution unit according to an embodiment of the present invention. The hardware execution unit includes a clutch module, a temperature sensing module, a water inlet control module, a drainage control module, a barrel collision detection module, a high-sensitivity acoustic array sensor, a microfluidic spray valve array and a micro heat pump energy recovery unit.

[0069] The clutch module receives control signals from the drive board to engage or disengage the washing drum and motor. During the wash or rinse cycle, the clutch module engages the motor, driving the reciprocating rotation of the pulsator. During the spin cycle, the clutch module engages the motor, driving high-speed rotation of the inner drum. For specific weighting or vibration suppression operations, the clutch module precisely switches according to command.

[0070] The temperature sensing module is configured to detect the water temperature signal inside each washing tub in real time. This module can use a thermistor, thermocouple, or integrated temperature sensor. The temperature probe is typically located at a predetermined location on the bottom or side of the washing tub to obtain accurate water temperature data. This module converts the detected analog signal into a digital signal and transmits it to the main control board via a communication interface.

[0071] The water inlet control module and the drain control module are each configured to receive control signals from the main control board. The water inlet control module includes a solenoid valve or proportional valve to precisely regulate the flow of cold water into each washing tub. The drain control module includes a drain valve and a drain pump to control the discharge of water from the washing tub. These two modules work together to precisely control the water level and volume within the washing tub, as well as coordinate operations during cooling, filling, and draining.

[0072] The drum collision detection module (vibration) is configured to monitor the relative position, vibration state, or deformation state of the washing drum in real time and output a drum collision risk signal. The drum collision detection module may include, but is not limited to, an acceleration sensor, a MEMS gyroscope, or a strain gauge. For example, an acceleration sensor can be installed on the outer wall or frame of the washing drum to measure the instantaneous acceleration of the washing drum during the dehydration process. When the detected acceleration or vibration amplitude exceeds a preset threshold, the module outputs a drum collision risk signal.

[0073] The highly sensitive acoustic array sensor consists of multiple miniature piezoelectric microphones or micro-electromechanical system (MEMS) microphones strategically placed on the outer wall of each washing drum. The microphone array, arranged in a circular or geometric configuration, is configured to capture broadband acoustic signals generated during washing machine operation in real time. The raw acoustic signals output by these sensors serve as input for the system's acoustic fingerprinting and fault diagnosis.

[0074] The microfluidic spray valve array integrates multiple miniature, high-response fluid spray valves in the annular area above each washing drum. Each spray valve is equipped with an independent drive circuit that can receive precise control instructions from the main control board to independently control the flow direction and spray pattern of extremely small flow rates. The flow control accuracy of the spray valve can reach the milliliter level. For example, the volume of liquid V sprayed per unit time t is spray Can be precisely controlled according to the instruction, that is, V spray =K·Δt, where K is the flow constant and Δt is the spray duration. This array is used to achieve point-to-point micro-liquid balancing and layered directional spray cooling.

[0075] The micro heat pump energy recovery unit is integrated into the drainage path of the washing machine and is configured to capture the waste heat of the high-temperature wastewater. The unit can be a miniaturized vapor compression heat pump or thermoelectric cooler (TEC) module, which transfers the heat energy of the high-temperature wastewater to the preheating medium. Its working principle is based on the refrigeration cycle, pumping heat from a low-temperature heat source to a high-temperature heat source. For example, the recovered heat Q rec It can be expressed as:

[0076] Q rec =m drain c water ·(T drain_in -T drain_out );

[0077] Where m drain is the drainage quality; c water is the specific heat capacity of water; T drain_in is the drainage temperature when entering the heat pump; T drain_out is the temperature of the drainage water when it leaves the heat pump.

[0078] The thermal energy storage unit is configured in conjunction with the micro heat pump energy recovery unit and is configured to store the low-grade thermal energy recovered by the micro heat pump energy recovery unit. The thermal energy storage unit can use a phase change material (PCM) as a heat storage medium, such as paraffin or hydrated salt, and use its phase change latent heat for energy storage. When the PCM solidifies from a liquid to a solid state, it releases latent heat, and when it melts from a solid state to a liquid state, it absorbs latent heat. The stored heat Q store It can be expressed as:

[0079] Q store=m pcm ·L pcm +m pcm c pcm ΔT sensible ;

[0080] Where m pcm is the mass of phase change material; L pcm is the latent heat of phase change material; c pcm is the specific heat capacity of the phase change material; ΔT sensible is the sensible temperature difference.

[0081] The preheating unit is configured to preheat a small amount of newly injected cold water using the energy stored in the thermal energy storage unit. The preheating unit can be a heat exchanger, and the newly injected cold water flows through the heat exchanger to exchange heat with the thermal energy storage unit, thereby increasing its temperature. For example, the temperature of the cold water after preheating is T preheated The following relationship is satisfied:

[0082]

[0083] Where, T cold_in is the initial temperature of cold water; Q transfer is the heat transferred from the thermal energy storage unit to the cold water; m cold The preheating unit transfers the stored heat energy to the cold water about to be injected into the washing tub through heat exchange, thereby reducing the additional energy input required for subsequent cooling or heating.

[0084] Please see the attached Figure 3 , Figure 3 This is a schematic diagram of a control processing unit according to an embodiment of the present invention. The control processing unit includes a main control board as a core hub for running software modules and a driver board for transmitting motor instructions.

[0085] The main control board is the core processing unit of the entire system, configured to receive and process various sensor data from the hardware execution unit and run all collaborative control software modules. The main control board is integrated with an AI chip with powerful computing power, which is configured to execute complex machine learning algorithms and real-time decision-making. The main control board receives input data from the temperature sensor module, the barrel collision detection module and the high-sensitivity acoustic array sensor through various communication interfaces, such as the serial peripheral interface (SPI), I2C bus or universal asynchronous receiver-transmitter (UART). At the same time, the main control board outputs digital signals or pulse width modulation (PWM) signals to control actuators such as the clutch module, water inlet control module, drainage control module and microfluidic spray valve array. The presence of the AI ​​chip on the main control board enables the system to process and analyze large-scale real-time data streams and generate optimized control instructions based on complex logic and models.

[0086] For example, the sensor data received by the main control board can be represented as a vector:

[0087] D sensor =[T water ,S impact-vibration ,S acoustic ,P motor-feedback ];

[0088] Where D sensor Indicates the sensor data received by the main control board; T water Represents the water temperature data measured by the temperature sensor module; S impact＿vibration Represents the vibration signal output by the barrel collision detection module; S acoustic represents the acoustic signal data collected by the high-sensitivity acoustic array sensor; P motor _ feedback Indicates the motor operating status parameters fed back by the driver board.

[0089] The main control board (with integrated AI chip) generates control instructions based on the received data and the software modules running inside. For example, the motor control instruction C output to the driver board motor It can be expressed as:

[0090] C motor =f(D sensor ,M software );

[0091] Where M software represents the current state and logic of the collaborative control software module; and function f represents the decision logic or algorithm inside the main control board.

[0092] The driver board is configured to receive motor commands output by the main control board and convert these high-level commands into low-level control signals that the motor driver can recognize and execute. The driver board typically contains power electronic devices (such as MOSFETs or IGBTs) and motor control chips, which are used to precisely control the operating parameters of the washing machine motor. These parameters include but are not limited to the motor's speed, rotation direction, start and stop, and specific micro-motion beats. The driver board is connected to the motor through power lines and signal lines. For example, the motor's speed is controlled by a PWM signal, and the rotation direction is controlled by changing the current direction. During the dehydration operation, the driver board ensures that the motor operates precisely according to the step acceleration curve or low-frequency micro-motion beat set by the main control board to achieve a stable dehydration process or precise engagement operation.

[0093] Please see the attached Figure 4 , Figure 4This is a schematic diagram of a collaborative control software module according to an embodiment of the present invention. The collaborative control software module runs on the main control board and includes an acoustic fingerprint recognition and fault diagnosis module, an intelligent fluid precision weighting and cooling module, an AI-driven collaborative decision-making and adaptive optimization module, and a micro heat pump energy recovery and precise temperature control linkage module.

[0094] The acoustic fingerprint recognition and fault diagnosis module is used to receive broadband acoustic wave signals collected by a high-sensitivity acoustic array sensor. This module uses a pre-trained deep learning model to extract features and perform pattern recognition on the acoustic wave signal. The deep learning model can be a convolutional neural network (CNN) or a recurrent neural network (RNN). This module determines the specific source and nature of the current vibration or abnormal noise in real time. The source and nature include clothing imbalance, abnormal bearing noise, motor failure, or minor collision. The judgment result is output in the form of diagnostic information, for example, a vector V representing the fault type is output. fault_type , where each component represents the probability or confidence of different faults.

[0095] The intelligent fluid precision weighting and cooling module (IFPCDM) is used to receive the diagnostic results of the acoustic fingerprint recognition and fault diagnosis module (AFDDM). Based on the diagnostic results, the module generates control instructions and sends them to the microfluidic spray valve array through the interface to achieve milliliter-level precise liquid weighting or layered directional spray cooling. When performing precise weighting, when the AFDDM recognizes that the clothes are unbalanced, the IFPCDM instructs the microfluidic spray valve array to spray water at the milliliter level to a specific area inside the washing drum according to the direction and degree of imbalance, and adjusts the center of gravity of the clothes in a point-to-point micro-liquid injection manner. When performing efficient cooling, combined with the feedback from the temperature sensing module, the IFPCDM dispatches the microfluidic spray valve array to accurately spray a small amount of cold water to the junction of the high-temperature water layer and the cold water layer in a layered directional spray mode, accelerating heat transfer without destroying the already formed water density gradient stratification.

[0096] Spray to the junction of high temperature water layer and cold water layer to accelerate heat transfer without destroying the formed water density gradient stratification. Spray water volume V spray The calculation can be based on the unbalance M unbalance and the unbalance angle θ unbalance ,Right now:

[0097] V spray =K1·M unbalance ·cos(θ unbalance );

[0098] Where K1 is the counterweight coefficient.

[0099] The AI-driven collaborative decision-making and adaptive optimization module is the core intelligent engine of the system, which is configured to integrate multiple modal data streams such as the diagnosis results from the acoustic fingerprint recognition and fault diagnosis module (AFDDM), the water temperature data from the temperature sensor module, the signal from the barrel detection module (vibration), and the motor operating parameters in real time. This module is based on reinforcement learning or deep reinforcement learning algorithms, such as deep Q network (DQN) or proximal policy optimization (PPO), and autonomously generates the optimal dehydration collaborative scheduling strategy and water cooling temperature control strategy through continuous interaction and feedback with the environment. The dehydration collaborative scheduling strategy includes timing, speed, clutch status, and preventive micro-weighting instructions of IFPCDM. The water cooling temperature control strategy includes water injection flow, spray mode, and drainage timing. The module is based on the current state S t and the reward function R(S t ,A t ), learn to generate the optimal action A t , maximizing the long-term cumulative rewards.

[0100] The micro-heat pump energy recovery and precision temperature control linkage module is configured to work with the drainage control module during the high-temperature drainage phase, instructing the micro-heat pump energy recovery unit to capture some of the waste heat from the high-temperature wastewater and store it in the thermal energy storage unit. When cold water is needed for cooling or when warm water is required for a specific wash mode, the AI-driven collaborative decision-making and adaptive optimization module directs the preheating unit to use the recovered heat energy to preheat the small amount of newly injected cold water. This module ensures efficient energy recycling within the system.

[0101] The dehydration coordination scheduling module is configured to generate instructions for coordinating the timing, speed, and clutch status of multiple drums to optimize dehydration stability. This module receives macro-scheduling instructions from the AI-driven collaborative decision-making and adaptive optimization module, and refines them into specific motor speed curves, clutch switching timing, etc., which are executed through the drive board and clutch module. For example, when dehydrating two drums at the same time, the start time difference Δt of the two drums can be adjusted to start To achieve timing staggering, that is:

[0102] t start2 =t start1 +Δt start ;

[0103] Where, t start1 and t start2 These are the dehydration start time for the first and second barrels respectively.

[0104] The dynamic water temperature adjustment module is configured to execute cooling logic based on the water temperature signal from the temperature sensing module to lower the water temperature. This module receives water temperature data and, based on preset safety thresholds and target temperatures, sends instructions to the water inlet and outlet control modules to control the injection of cold water and the discharge of hot water. It collaborates with the intelligent fluid precision balancing and cooling module to achieve an efficient and safe cooling process.

[0105] The barrel collision risk monitoring and avoidance module is configured to analyze the signals of the barrel collision detection module (vibration) and the diagnostic results of the acoustic fingerprint recognition and fault diagnosis module in real time to evaluate the collision risk level. When a potential risk is detected, the module generates avoidance instructions. The avoidance instructions include speed reduction and shutdown for the faulty washing drum, quantitative water injection and cooling, clutch state switching, and high-frequency jitter beat imbalance processing. At the same time, for non-faulty washing drums, the module generates a strategy to maintain operating efficiency to minimize unnecessary interference to the normally operating washing drum. The barrel collision risk monitoring and avoidance module is linked to the dehydration collaborative scheduling module to ensure that while avoiding risks, the continuity of the overall washing task is maintained as much as possible.

[0106] Refer to the attached Figure 5 , Figure 5 This is a flow chart of an intelligent control method for an energy-saving twin-tub washing machine according to one embodiment of the present invention. The method is applied to the intelligent control system of the energy-saving twin-tub washing machine of the present invention, and the method includes the following steps:

[0107] S1, water temperature detection and cooling logic execution;

[0108] At certain stages of the washing cycle, such as at the end of washing or rinsing and before draining, the temperature sensing module in the system detects the water temperature inside each washing tub in real time. The temperature sensing module transmits the detected water temperature signal to the main control board. If the water temperature exceeds a preset safety threshold, such as T safe_threshold , the main control board (with integrated AI chip) executes the cooling logic through the water temperature dynamic adjustment module and the AI-driven collaborative decision-making and adaptive optimization module.

[0109] Specifically, the drainage control module first closes the drain valve to ensure that the water in the barrel is in a relatively static state. Subsequently, the water inlet control module and the microfluidic spray valve array work together to inject cold water to the preset cooling water level according to the decision instructions of the AI-driven collaborative decision-making and adaptive optimization module. In this process, the intelligent fluid precision weighting and cooling module uses a layered directional spray mode to accurately spray a small amount of cold water to the junction of the high-temperature water layer and the cold water layer through the microfluidic spray valve array. During the spraying process, the impeller remains stationary, and the water density gradient is used to achieve natural sedimentation of the cold water, thereby accelerating the heat transfer inside the water body with zero impeller stirring energy consumption, forming a low-temperature layer at the bottom.

[0110] When the temperature sensing module detects that the bottom temperature is less than or equal to the first threshold, the AI-driven collaborative decision-making and adaptive optimization module will synchronously instruct the drainage control module to open the drainage valve and continuously instruct the water inlet control module to inject cold water for injection and drainage collaborative heat exchange. target_bottom Next, the AI-driven collaborative decision-making and adaptive optimization module forces the inlet valve to remain open to continuously inject water until the overall water temperature in the bucket reaches a preset high-temperature threshold, at which point the drain valve opens to force drainage. If the water temperature remains below or equal to a second threshold, injection stops.

[0111] S2. Dehydration command is sent and the coordinated dehydration state is entered;

[0112] When the water temperature in the bucket reaches the safety threshold and the water in the bucket is completely drained, the main control board (with an integrated AI chip) sends a dehydration command. After receiving the dehydration command, the system enters the coordinated dehydration state and prepares for subsequent dehydration operations.

[0113] S3, continuous monitoring and dynamic adjustment of operating status;

[0114] During the collaborative dehydration process, the system continuously monitors the operating status of each washing drum, including vibration and abnormal noise. The acoustic fingerprint recognition and fault diagnosis module (AFDDM) receives the original wide-band sound wave signal collected by the high-sensitivity acoustic array sensor. AFDDM uses a deep learning model to extract features and recognize patterns of sound wave signals, and identifies the specific source and nature of the current vibration or abnormal noise in real time. The source and nature include clothing imbalance, abnormal bearing noise, motor failure or minor collision. The AI-driven collaborative decision-making and adaptive optimization module dynamically adjusts the monitoring sensitivity of the barrel collision detection module (vibration) based on the results of the AFDDM judgment and the signal of the barrel collision detection module (vibration), such as adjusting the acceleration threshold according to the current vibration spectrum characteristics.

[0115] S4, optimal dehydration coordinated scheduling strategy generation and execution;

[0116] The AI-driven collaborative decision-making and adaptive optimization module analyzes diagnostic results from the AFDDM, signals from the barrel collision detection module (vibration), and motor operating parameters in real time. Based on this real-time data and internal optimization algorithms, the module dynamically generates the optimal dehydration collaborative scheduling strategy and instructs the drive board and clutch module to execute it.

[0117] The specific implementation of this strategy involves the following: The AI-driven collaborative decision-making and adaptive optimization module outputs a coordinated signal to the drive board through the dehydration collaborative scheduling module. The driver board controls the clutch module to switch to the dehydration state and triggers a low-frequency micro-motion beat to ensure clutch engagement and reduce shock. The first drum (the washing drum currently scheduled for dehydration) is controlled to execute a stepped acceleration dehydration profile, gradually increasing the spin speed. If the AFDDM identifies a slight imbalance in any drum, the AI-driven collaborative decision-making and adaptive optimization module instructs the intelligent fluid precision weighting and cooling module to perform preventative micro-liquid weighting via the microfluidic spray valve array, intervening before vibration escalates. If the second drum needs to drain while the first drum is dehydrating at high speed, the AI-driven collaborative decision-making and adaptive optimization module instructs the second drum to pause its draining operation and use it as a static counterweight to suppress any disturbances that may be superimposed on the first drum's high-speed dehydration. After the first drum completes dehydration, the AI-driven collaborative decision-making and adaptive optimization module instructs the second drum to dehydrate at high speed or adjusts its dehydration parameters based on real-time system status and load conditions.

[0118] S5. Barrel collision risk assessment and chain response avoidance;

[0119] The system continuously determines whether there is a barrel collision risk. If the barrel collision detection module (vibration) issues a barrel collision signal or the high-sensitivity acoustic array sensor captures the unique acoustic fingerprint of a barrel collision, AFDDM accurately diagnoses the specific cause of the barrel collision. Based on the AFDDM diagnosis, the AI-driven collaborative decision-making and adaptive optimization module executes chained response avoidance instructions through the barrel collision risk monitoring and avoidance module.

[0120] The avoidance instructions include: controlling the faulty washing drum to slow down to a stop, instructing the intelligent fluid precision weighting and cooling module to inject water for weighting through the microfluidic spray valve array, switching the clutch module to the washing state, and the driver board to unbalance the faulty washing drum and output a high-frequency jitter beat to redistribute the clothes. At the same time, based on the current operating status of the non-faulty washing drum, the AI-driven collaborative decision-making and adaptive optimization module maximizes its operating efficiency to avoid unnecessary downtime or interruptions, such as allowing it to continue to complete the current washing or rinsing task. When the clutch module state switches, the driver board triggers a low-frequency micro-motion beat to ensure engagement accuracy and reduce component wear.

[0121] S6, the washing cycle ends;

[0122] When the dehydration operations of all washing drums are completed, the system ends the current washing cycle and enters the standby state or the preparation stage for the next washing cycle.

[0123] In order to further illustrate the collaborative working process of the technical solution of the present invention, a specific working scenario example will be used below to illustrate.

[0124] When the user selects the wash mode and starts the twin-drum washing machine, the system first enters the water temperature detection and control phase. During this phase, the temperature sensing module continuously monitors the water temperature inside each drum. If the water temperature in any drum exceeds a preset threshold, for example, after a high-temperature wash or rinse cycle, the dynamic water temperature adjustment module and the AI-driven collaborative decision-making and adaptive optimization module in the main control board (with an integrated AI chip) initiate cooling logic.

[0125] The specific operation is that the drainage control module first closes the drain valve to maintain the water in the barrel. Subsequently, the water inlet control module and the microfluidic spray valve array work together to inject cold water into the washing tub according to the instructions of the AI-driven collaborative decision-making and adaptive optimization module. The intelligent fluid precision weighting and cooling module will accurately control the microfluidic spray valve array to spray cold water to the junction of the high-temperature water layer and the cold water layer in a layered directional spray mode. During this cooling process, the impeller remains stationary and uses the density difference of the water body to cause the cold water to settle naturally, thereby achieving heat exchange. When the temperature sensing module detects that the bottom water temperature drops below the safe drainage threshold, the AI-driven collaborative decision-making and adaptive optimization module will simultaneously instruct the drainage control module to open the drain valve and continuously instruct the water inlet control module to inject cold water, forming a collaborative heat exchange of injection and drainage to ensure safe drainage. After reaching the target temperature, the system stops water intake and drains all the water in the barrel.

[0126] After water temperature processing and drainage are complete, the system enters the dehydration phase. The main control board sends a dehydration command, and the system enters the coordinated dehydration state. During the dehydration process, a highly sensitive acoustic array sensor and a drum collision detection module continuously monitor the operating status of the washing drum in real time, including vibrations and possible abnormal noise. The Acoustic Fingerprint Recognition and Fault Diagnosis Module (AFDDM) receives acoustic data and analyzes it using its built-in deep learning model to determine in real time whether there are specific fault sources such as clothing imbalance, abnormal bearing noise, or minor collisions.

[0127] If AFDDM identifies a slight imbalance in a washing tub, the AI-driven collaborative decision-making and adaptive optimization module immediately generates a preventative micro-liquid rebalancing command. This command, through the intelligent fluid precision rebalancing and cooling module, precisely controls the microfluidic spray valve array to spray milliliter-level water flow to specific areas within the washing tub, adjusting the center of gravity of the clothes in a point-to-point manner, thus intervening before the imbalance escalates.

[0128] When two washing drums are spinning simultaneously, the AI-driven collaborative decision-making and adaptive optimization module intelligently schedules the spin sequence of the two washing drums. For example, if the first drum is spinning at high speed and the second drum needs to be drained, the AI-driven collaborative decision-making and adaptive optimization module will instruct the second drum to suspend draining, using it as a static counterweight to offset or suppress the vibration that may be generated by the first drum's high-speed spin. After the first drum is finished spinning, the system will schedule the second drum to spin based on the real-time status.

[0129] If during the dehydration process, the barrel collision detection module sends a barrel collision signal or the high-sensitivity acoustic array sensor captures the unique acoustic fingerprint of the barrel collision, AFDDM will perform an accurate diagnosis. The AI-driven collaborative decision-making and adaptive optimization module will execute chain response avoidance instructions through the barrel collision risk monitoring and avoidance module based on the diagnosis results. For example, for a faulty washing drum, the system will instruct it to slow down to a stop, and inject a precise amount of water for cooling through the intelligent fluid precision weighting and cooling module, and switch the clutch module to the washing state. The drive board will perform high-frequency jitter beat imbalance processing on the faulty washing drum to redistribute the clothes. At the same time, for washing drums that have not failed, the AI-driven collaborative decision-making and adaptive optimization module will maximize its operating efficiency, avoid unnecessary downtime, and thus ensure the continuity of the washing task. When the clutch module state switches, the drive board will trigger a low-frequency micro-motion beat to ensure engagement accuracy.

[0130] During the high-temperature drainage phase, the micro heat pump energy recovery unit captures the wastewater's excess heat and stores it in a thermal energy storage unit. When cold water is subsequently needed for cooling, or when warm water is required for a specific wash mode, the AI-driven collaborative decision-making and adaptive optimization module dispatches the preheating unit, utilizing the stored thermal energy to preheat the newly injected cold water. This creates an internal energy cycle and reduces external energy input.

[0131] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent control system for an energy-saving twin-drum washing machine, characterized in that: include: The hardware execution unit includes a clutch module, a temperature sensor module, a water inlet control module, a water discharge control module, a barrel collision detection module, a high-sensitivity acoustic array sensor, a microfluidic spray valve array, and a micro heat pump energy recovery unit, providing multimodal sensing, precise liquid management, mechanical execution, and energy recovery capabilities. The control processing unit, which includes a main control board that serves as the core hub for running software modules and a driver board that transmits motor commands, is used to process received data, run algorithms, and coordinate the operations of various system components; The collaborative control software module runs on the main control board and includes: an acoustic fingerprint recognition and fault diagnosis module, configured to receive the acoustic wave signals collected by the high-sensitivity acoustic array sensor and identify the source and nature of vibration or abnormal noise; Intelligent fluid precision balancing and cooling module, used for liquid balancing or layered directional spray cooling through a microfluidic spray valve array; An AI-driven collaborative decision-making and adaptive optimization module is used to integrate the diagnostic results from the acoustic fingerprint recognition and fault diagnosis module, the water temperature data from the temperature sensor module, the signal from the barrel collision detection module, and the motor operating parameters in real time to autonomously generate a dehydration collaborative scheduling strategy and a water cooling temperature control strategy; The micro heat pump energy recovery and precise temperature control linkage module is used to cooperate with the drainage control module to capture waste heat and preheat the newly injected cold water by recovering heat energy.

2. The intelligent control system for an energy-saving twin-tub washing machine according to claim 1, characterized in that: The high-sensitivity acoustic array sensor is set on the outer wall of each washing tub to collect the broadband acoustic wave signals generated during the operation of the washing machine in real time; the microfluidic spray valve array is integrated in the upper annular area of ​​each washing tub, and each valve of the microfluidic spray valve array can independently control the flow direction and spray pattern of extremely small flow rates.

3. The intelligent control system for an energy-saving twin-tub washing machine according to claim 1, characterized in that: The acoustic fingerprint recognition and fault diagnosis module includes using a deep learning model to extract features and recognize patterns on the received raw sound wave signals to determine the specific source and nature of the current vibration or abnormal noise in real time. The source and nature include clothing imbalance, abnormal bearing noise, motor failure or minor collision.

4. The intelligent control system for an energy-saving twin-tub washing machine according to claim 1, characterized in that: The intelligent fluid precise weight balancing and cooling module includes: When the acoustic fingerprint recognition and fault diagnosis module identifies that the clothes are unbalanced, it instructs the microfluidic spray valve array to spray water at the milliliter level to a specific area inside the washing drum according to the direction and degree of the imbalance, performing point-to-point micro-liquid balancing. When the temperature sensing module detects that the water temperature exceeds the standard, it intelligently dispatches the microfluidic spray valve array to precisely spray a small amount of cold water to the junction of the high-temperature water layer and the cold water layer in a layered directional spray mode, accelerating heat transfer without destroying the already formed water density gradient stratification.

5. The intelligent control system for an energy-saving twin-tub washing machine according to claim 1, characterized in that: The AI-driven collaborative decision-making and adaptive optimization module includes: Based on reinforcement learning or deep reinforcement learning algorithms, it integrates vibration source root cause diagnosis information from the acoustic fingerprint recognition and fault diagnosis module, water temperature data from the temperature sensor module, displacement deformation data from the barrel collision detection module, and motor operating parameters in real time; Through continuous learning and optimization, the optimal dehydration collaborative scheduling strategy and water cooling temperature control strategy are autonomously generated. The dehydration collaborative scheduling strategy includes timing, speed, clutch status, and preventive micro-weighting instructions for the intelligent fluid precise weighting and cooling module.

6. The intelligent control system for an energy-saving twin-tub washing machine according to claim 1, characterized in that: The micro heat pump energy recovery unit also includes: a thermal energy storage unit coordinated with the micro heat pump energy recovery unit, for storing recovered low-grade thermal energy; The preheating unit is used to preheat a small amount of newly injected cold water by utilizing the energy in the thermal energy storage unit.

7. The intelligent control system for an energy-saving twin-tub washing machine according to claim 1, characterized in that: The collaborative control software module also includes a dehydration collaborative scheduling module, a water temperature dynamic adjustment module, and a barrel collision risk monitoring and avoidance module; The avoidance instructions generated by the drum collision risk monitoring and avoidance module include speed reduction and shutdown for faulty washing drums, quantitative water injection cooling, clutch state switching, high-frequency jitter beat imbalance processing, and maintenance of operating efficiency strategies for non-faulty washing drums.

8. An intelligent control method for an energy-saving twin-tub washing machine, applied to the intelligent control system of an energy-saving twin-tub washing machine according to any one of claims 1 to 7, characterized in that: The following steps are involved: S1: The system detects the water temperature inside each washing tub and executes cooling logic based on whether the water temperature reaches the safety threshold; S2: When the water temperature in the barrel reaches the safety threshold and the water in the barrel is emptied, the intelligent control system sends a dehydration command and enters the coordinated dehydration state; S3: During the coordinated dehydration process, the intelligent control system continuously monitors the operating status of the washing drum, including vibration and abnormal noise, and dynamically adjusts the monitoring sensitivity; S4: The intelligent control system analyzes the monitoring data in real time and dynamically generates an optimal dehydration coordination scheduling strategy based on the analysis results. The strategy includes imbalance processing and coordination among multiple buckets. S5: The intelligent control system determines whether there is a barrel collision risk; if so, it accurately diagnoses the cause of the barrel collision and executes chain response avoidance instructions; S6: After the dehydration is completed, the current washing cycle ends.

9. The intelligent control method for an energy-saving twin-tub washing machine according to claim 8, characterized in that: In step S1, the cooling logic is executed according to whether the water temperature reaches the safety threshold, including: If the water temperature does not reach the safety threshold, the drainage module is controlled to close the drainage valve. The water inlet control module and the microfluidic spray valve array work together to inject cold water and spray it precisely in a layered and directional spray mode, keeping the impeller stationary to form a low-temperature layer at the bottom. When it is detected that the bottom temperature is less than or equal to the first threshold, the drain valve is opened synchronously and cold water is continuously injected for injection and drainage coordinated heat exchange; when the water temperature is continuously less than or equal to the second threshold, water injection is stopped, and the first threshold is greater than the second threshold.

10. The intelligent control method for an energy-saving twin-tub washing machine according to claim 8, characterized in that: The method further comprises the following steps: The acoustic fingerprint recognition and fault diagnosis module receives the original sound wave signal collected by the high-sensitivity acoustic array sensor, uses the deep learning model to perform feature extraction and pattern recognition, and determines the specific source and nature of the current vibration or abnormal noise in real time; The AI-driven collaborative decision-making and adaptive optimization module dynamically adjusts the monitoring sensitivity of the barrel crash detection module based on the results of the acoustic fingerprint recognition and fault diagnosis module and the signal of the barrel crash detection module.

Images