Self-adaptive starting method and system for fire-fighting vehicle in low-temperature environment

Abstract

The invention provides a self-adaptive starting method and system for a fire-fighting vehicle in a low-temperature environment, and the method comprises the steps: S1, obtaining real-time temperature data from the environment and each key part of the fire-fighting vehicle through a sensor array, judging whether the fire-fighting vehicle is in a low-temperature state or not through a threshold comparison method according to the collected temperature distribution, and obtaining a low-temperature activation signal; s3, if any element in the deviation matrix exceeds a preset deviation threshold value, integrating the elements of the deviation matrix to generate a power adjusting instruction, and obtaining a dynamic power output sequence; s4, a dynamic power output sequence is adopted to drive multiple heaters to conduct parallel heating on an engine cylinder body and a fuel oil pipeline, meanwhile, the temperature change rate in the heating process is monitored, and the heating balance degree is judged; and S7, acquiring a starting preparation signal from the vehicle control unit according to the coordination completion mark, releasing the starting sequence if the temperature coordination index reaches a preset index threshold value, and judging the response capability of the vehicle. According to the invention, the quick response capability of the vehicle in an extreme environment is obviously improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology for fire trucks, and in particular to an adaptive starting method and system for fire trucks in low-temperature environments. Background Technology

[0002] As core equipment for responding to emergencies such as fires, the reliability and rapid response capability of fire trucks in extreme environments are crucial for ensuring public safety. In frigid regions, fire trucks need to start up and be deployed quickly in extremely low temperatures; any delay could lead to rescue failure. However, current fire truck preheating systems have significant limitations in dealing with extreme low-temperature environments. Many existing solutions rely too heavily on a single heating method or fixed power output, making it difficult to adapt to dynamic changes in ambient temperature, and they lack comprehensive protection for critical components such as fuel lines, hydraulic systems, and water pumps. This results in excessively long start-up times for vehicles in environments with temperatures tens of degrees below zero, and even prevents them from operating normally due to component freezing.

[0003] In frigid environments, the core challenges facing fire trucks lie in achieving rapid system startup and comprehensive protection of critical components. The primary issue is the insufficient power regulation capability of the preheating system. Traditional preheating devices typically use fixed-power heating, unable to dynamically adjust according to changes in ambient temperature. This results in low heating efficiency at extremely low temperatures or energy waste at higher temperatures. For example, in an environment of -40 degrees Celsius, a fixed-power heater may take tens of minutes to heat the engine block to the required startup temperature, while rescue missions often require vehicles to be operational within minutes. This limitation in power regulation further leads to a second problem: the difficulty of coordinated temperature management for critical components. The engine, fuel lines, hydraulic system, and water pump of a fire truck have different temperature requirements, and a single heating method cannot simultaneously meet the operating conditions of these components. For example, an insufficiently preheated water pump may be damaged due to internal freezing, while overheating of the hydraulic system may lead to abnormal oil viscosity, affecting the precise operation of the ladder.

[0004] Therefore, designing an integrated preheating system that can dynamically adjust the preheating power according to the ambient temperature and simultaneously achieve coordinated temperature management of key components such as the engine, fuel lines, hydraulic system and water pump has become a key issue for the rapid response and reliable operation of fire trucks in frigid environments. Summary of the Invention

[0005] A first aspect of the present invention provides an adaptive starting method for fire trucks in low-temperature environments, the method comprising:

[0006] S1. Real-time temperature data is acquired from the environment and key components of the fire truck using a sensor array. A threshold comparison method is used to determine if the system is in a low-temperature state based on the collected temperature distribution, generating a low-temperature activation signal. S2. Based on the low-temperature activation signal, the target temperature ranges for the engine fuel line hydraulic system and water pump are obtained from a preset temperature demand model. The deviation between the current temperature and the target temperature is calculated, and a deviation matrix is ​​determined. S3. If any element in the deviation matrix exceeds a preset deviation threshold, the elements of the deviation matrix are integrated to generate a power adjustment command, resulting in a dynamic power output sequence. S4. The dynamic power output sequence is used to drive multiple heaters to heat the engine block and fuel lines in parallel. Simultaneously monitor the temperature change rate during the heating process to determine the heating uniformity; S5, obtain real-time updated data from the temperature sensors of the hydraulic system and water pump based on the heating uniformity. If the change rate is lower than the preset rate threshold, adjust the power distribution ratio and determine the optimized heating path; S6, synchronously activate the auxiliary heating module through the optimized heating path to circulate and preheat the fluid inside the water pump. Combine the updated version of the deviation matrix to calculate the overall system temperature coordination index and obtain the coordination completion flag; S7, obtain the start-up preparation signal from the vehicle control unit based on the coordination completion flag. If the temperature coordination index reaches the preset index threshold, release the start-up sequence and determine the vehicle's response capability.

[0007] Optionally, in step S3, if any element in the deviation matrix exceeds a preset deviation threshold, the elements of the deviation matrix are integrated to generate a power adjustment command, resulting in a dynamic power output sequence, including:

[0008] Step S31: If any element of the deviation matrix exceeds the preset deviation threshold, the excess element is extracted to generate deviation distribution data.

[0009] Step S32: Process the deviation distribution data through a proportional-integral-derivative controller, calculate the power control parameters, and obtain the power adjustment command;

[0010] Step S33: Adjust the power output according to the power adjustment command to generate an initial power output sequence;

[0011] Step S34: If there is a deviation between the initial power output sequence and the target output sequence, calculate the sequence deviation value and obtain the deviation correction data;

[0012] Step S35: Smooth the deviation correction data to generate an optimized power output sequence;

[0013] Step S36: Adjust the power distribution according to the optimized power output sequence to obtain the final power output sequence;

[0014] Step S37: If the final power output sequence meets the preset performance threshold, then store the sequence data and generate a dynamic power control log.

[0015] Optionally, step S32, which processes the deviation distribution data using a proportional-integral-derivative controller to calculate power control parameters and obtain a power adjustment command, includes:

[0016] Calculate the power control parameters using the following formula:

[0017] ,

[0018] in, These are power control parameters. It is the proportionality coefficient. It is the difference between the biased distribution data and zero. It is the integral coefficient. yes Integral over time, These are differential coefficients. It is the derivative of e with respect to time.

[0019] Optionally, in step S34, if there is a deviation between the initial power output sequence and the target output sequence, the sequence deviation value is calculated to obtain deviation correction data, including: the sequence deviation value is the difference sequence between the initial power output sequence and the target output sequence.

[0020] Optionally, step S35, which smooths the deviation correction data to generate an optimized power output sequence, includes:

[0021] Calculate the deviation correction data using the following formula:

[0022] ,

[0023] Wherein, the state vector x is the bias correction data, x' is the prediction bias correction data, K is the Kalman gain, z is the measurement value, and H is the measurement matrix.

[0024] Optionally, the prediction bias correction data can be calculated using the following formula:

[0025] x'=Fx+u

[0026] Where F is the state transition matrix and u is the power control parameter.

[0027] Optionally, step S5 involves obtaining real-time updated data from the temperature sensors of the hydraulic system and water pump based on the heating uniformity. If the rate of change is lower than a preset rate threshold, the power distribution ratio is adjusted to determine the optimized heating path, including:

[0028] Step S51: Obtain real-time data from the temperature sensors of the hydraulic system and water pump;

[0029] Step S52: Calculate the time-series temperature values ​​of each sensor, where the time-series temperature values ​​are the reading sequences of the sensors at different time points;

[0030] Step S53: Calculate the real-time heating uniformity based on the time series temperature values;

[0031] Step S54: If the real-time heating uniformity is lower than the preset second uniformity threshold, then the temperature data is clustered. First, the temperature data is standardized, then the number of clusters is set to 3. After clustering, the cluster with the lowest temperature is determined as the abnormal region, and the distribution of abnormal regions is obtained.

[0032] Step S55: Calculate the rate of temperature change in each region based on the distribution of abnormal regions;

[0033] Step S56: Determine whether the rate of change is lower than a preset rate threshold to obtain the rate abnormality region;

[0034] Step S57: If there is a rate anomaly region, predict the power adjustment range and determine the power allocation ratio.

[0035] Step S58: Adjust the power distribution of the hydraulic system and water pump according to the power distribution ratio, and generate new control commands;

[0036] Step S59: Obtain new real-time data from the temperature sensor, calculate the updated real-time heating uniformity, determine whether the preset second uniformity threshold has been reached, and obtain the system operating status.

[0037] Optionally, step S53, calculating the real-time heating uniformity based on the time-series temperature values, includes:

[0038] Calculate real-time heating uniformity using the following formula:

[0039] ,

[0040] Where E is the real-time heating uniformity, T is the temperature value sequence, max(T) is the maximum temperature, min(T) is the minimum temperature, and avg(T) is the average temperature.

[0041] Optionally, step S55, calculating the temperature change rate of each region based on the distribution of abnormal regions, includes:

[0042] Calculate the rate of temperature change using the following formula:

[0043] ,

[0044] Where R is the rate of temperature change. This is the current temperature. Δt represents the temperature at the previous time, and Δt represents the time interval.

[0045] A second aspect of the present invention provides an adaptive starting system for fire trucks in low-temperature environments. The system employs the method described above to enable adaptive starting of fire trucks in low-temperature environments. The system includes: a temperature monitoring module, used to acquire real-time temperature data from the environment and key components of the fire truck via a sensor array, and to determine whether the vehicle is in a low-temperature state based on a threshold comparison method according to the collected temperature distribution, thereby obtaining a low-temperature activation signal; a temperature demand analysis module, used to obtain the target temperature ranges for the engine fuel line hydraulic system and water pump from a preset temperature demand model based on the low-temperature activation signal, and to calculate the deviation between the current temperature and the target temperature using an algorithm to determine a deviation matrix; a power control module, used to integrate the elements of the deviation matrix to generate a power adjustment command if any element in the deviation matrix exceeds a preset deviation threshold, thereby obtaining a dynamic power output sequence; and a heating execution module. The system comprises four modules: a module for driving multiple heaters to heat the engine block and fuel lines in parallel using a dynamic power output sequence, and a module for monitoring the rate of temperature change during heating to determine the degree of heating evenness; a balance monitoring module for obtaining real-time updated data from temperature sensors in the hydraulic system and water pump based on the degree of heating evenness, adjusting the power distribution ratio if the rate of change is lower than a preset threshold, and determining an optimized heating path; a path optimization module for synchronously activating the auxiliary heating module to circulate and preheat the fluid inside the water pump using the optimized heating path, calculating the overall system temperature coordination index based on the updated version of the deviation matrix, and obtaining a coordination completion flag; and a coordination start module for obtaining a start preparation signal from the vehicle control unit based on the coordination completion flag, releasing the start sequence if the temperature coordination index reaches a preset index threshold, and determining the vehicle's responsiveness.

[0046] The technical solution provided by this invention has the following beneficial effects:

[0047] This invention discloses an adaptive starting method and system for fire trucks in low-temperature environments. By real-time acquisition of ambient and vehicle key component temperatures, the system determines the low-temperature state and generates an activation signal. A deviation matrix is ​​calculated using a preset temperature demand model. Then, a dynamic power output sequence is generated through a proportional-integral-derivative control algorithm to drive multiple heaters to heat the engine and fuel lines in parallel. Simultaneously, the temperature change rate is monitored to optimize the heating path and activate auxiliary heating modules. Finally, a temperature coordination index is used to determine start-up readiness and release the start-up sequence. This invention solves the technical problem of slow start-up response of fire trucks in low-temperature environments through multi-system coordinated heating and dynamic power adjustment, significantly improving the vehicle's rapid response capability and operational reliability in extreme environments. Attached Figure Description

[0048] Figure 1 This is a flowchart of an adaptive starting method for fire trucks in low-temperature environments according to the present invention.

[0049] Figure 2 This is a schematic diagram of an adaptive starting method for fire trucks in low-temperature environments according to the present invention.

[0050] Figure 3 This is another schematic diagram of an adaptive starting method for fire trucks in low-temperature environments according to the present invention.

[0051] Figure 4 This is a schematic diagram of the structure of an adaptive starting system for fire trucks in low-temperature environments according to the present invention. Detailed Implementation

[0052] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] like Figures 1-3 As shown, in a first aspect, the present invention provides an adaptive starting method for fire trucks in low-temperature environments, the method comprising:

[0054] S1 acquires real-time temperature data from the environment and key components of the fire truck through a sensor array. Based on the collected temperature distribution, a threshold comparison method is used to determine whether the temperature is in a low-temperature state, and a low-temperature activation signal is obtained.

[0055] Optionally, this step also includes:

[0056] Step S11: Real-time temperature data is acquired from the environment and key components of the fire truck through a sensor array and stored as the first temperature dataset.

[0057] Step S12: Based on the first temperature dataset, use NumPy's mean function to calculate the average temperature of the environment and vehicle components, and generate the first temperature distribution feature.

[0058] Step S13: If the first temperature distribution characteristic is lower than the preset temperature distribution threshold, then the first low temperature state is determined by threshold comparison.

[0059] Step S14: Calculate the duration and intensity of the first low temperature state based on the first low temperature state, and generate the first continuous dataset.

[0060] Step S15: Based on the first persistent dataset, use the K-Means algorithm to classify the duration and intensity of the first low-temperature state, and generate a second classification result.

[0061] Step S16: If the second classification result shows that the duration of the first low temperature state exceeds the preset duration threshold, then generate a first alarm signal and store it as a first alarm dataset.

[0062] Step S17: Based on the first alarm dataset, the first alarm signal is sent to the fire truck control system via the serial port transmission module.

[0063] Specifically, sensor array data acquisition is a fundamental component of the fire truck low-temperature monitoring system.

[0064] In one embodiment, the fire truck is equipped with multiple temperature sensors distributed in key areas such as the engine compartment, water pump system, water tank, and hydraulic system, while an ambient temperature sensor monitors changes in the outside air temperature. These sensors collect temperature data once per second, forming a first temperature dataset that includes timestamps and temperature values.

[0065] For example, during a winter operation, the sensor array collected 1800 data points within 30 minutes, covering multiple dimensions of information such as engine temperature, water tank temperature, and ambient temperature. The calculation of the first temperature distribution characteristic used NumPy's mean function to perform statistical analysis on the collected data.

[0066] Specifically, the system calculates the average value of temperature data from each sensor within the same time period to generate characteristic parameters that reflect the overall temperature situation.

[0067] For example, when the ambient temperature is -15 degrees Celsius, the engine compartment temperature is 5 degrees Celsius, and the water pump system temperature is -8 degrees Celsius, the calculated average temperature is -6 degrees Celsius. This processing method can effectively eliminate the interference of single-point outlier data and improve the accuracy of temperature assessment. The threshold comparison mechanism is a key technology for determining the first cryogenic state.

[0068] In one possible implementation, the system presets multiple temperature distribution thresholds, including a mild low temperature threshold of -5 degrees Celsius, a moderate low temperature threshold of -10 degrees Celsius, and a severe low temperature threshold of -20 degrees Celsius. When the first temperature distribution characteristic falls below the corresponding threshold, the system automatically determines that it has entered the corresponding level of low temperature state. This hierarchical determination method enables refined low temperature state identification, providing an accurate basis for subsequent processing. The generation of the first persistent dataset involves the quantitative calculation of the duration and intensity of the low temperature state.

[0069] For example, when the system detects that the temperature has remained below -10 degrees Celsius for 20 minutes, the duration parameter is recorded as 1200 seconds, and the intensity parameter is calculated based on the degree of temperature deviation from the threshold. The intensity calculation considers both the magnitude of temperature deviation and sustained stability to form a comprehensive evaluation index. K-Means algorithm classification is the core technology for intelligent analysis of low-temperature conditions.

[0070] In one embodiment, the system uses duration and intensity as two-dimensional feature vectors and uses the K-Means algorithm to classify the cryogenic state into three categories: short-term mild, moderate and persistent, and long-term severe.

[0071] For example, situations lasting 5 minutes and with low intensity are classified as short-term and mild, while situations lasting more than 30 minutes and with high intensity are classified as long-term and severe. This classification method can automatically identify different types of low-temperature threats, improving the targeting of early warnings. The generation of the first alarm signal is based on intelligent judgment of the classification results.

[0072] Specifically, when the second classification result indicates that the low temperature condition belongs to the prolonged severe category and the duration exceeds the preset 25-minute threshold, the system immediately generates a first alarm signal. The alarm signal contains detailed information such as the low temperature level, duration, and affected components, and is stored as a structured first alarm dataset. A serial port transmission module ensures reliable transmission of the alarm signal.

[0073] In one possible implementation, the system sends the first alarm signal to the fire truck control system via the RS485 serial port protocol at a transmission rate of 9600 baud, ensuring the real-time performance and stability of the signal transmission. This design enables effective linkage between the low-temperature monitoring system and the vehicle control system, allowing for timely activation of anti-freezing protection measures.

[0074] S2: Based on the low temperature activation signal, obtain the target temperature ranges of the engine fuel line hydraulic system and water pump from the preset temperature demand model, and use a linear interpolation algorithm to calculate the deviation between the current temperature and the target temperature to determine the deviation matrix.

[0075] Optionally, this step also includes:

[0076] Step S21: When the low temperature activation signal is triggered, obtain the target temperature range of the engine fuel line hydraulic system and water pump from the preset temperature requirement database, and determine the target temperature range.

[0077] Step S22: Calculate the deviation between the current temperature and the target temperature range by subtracting the lower or upper limit of the target temperature range from the current temperature, and obtain the temperature deviation.

[0078] Step S23: Based on the temperature deviation, use the NumPy array tool to generate a deviation matrix that includes the engine fuel line hydraulic system and water pump, and determine the deviation matrix.

[0079] Step S24: If any deviation value in the deviation matrix exceeds the preset temperature deviation threshold, the corresponding temperature regulation strategy is obtained from the preset regulation strategy database using the decision tree algorithm, and the regulation strategy is obtained.

[0080] Step S25: Based on the adjustment strategy, generate control commands to adjust the operating parameters of the engine fuel line hydraulic system and water pump to obtain the adjusted parameters.

[0081] Step S26: Obtain the real-time current temperature using the adjusted parameters, calculate the new temperature deviation value from the target temperature range, and obtain the updated temperature deviation.

[0082] Step S27: If the updated temperature deviation exceeds the preset temperature deviation threshold, then a new deviation matrix is ​​generated using the NumPy array tool based on the updated temperature deviation, and the new deviation matrix is ​​determined.

[0083] In one embodiment, a preset temperature requirement database stores the standard operating temperature ranges for various key components of the fire truck. The target temperature range for the engine is typically set to 80 to 95 degrees Celsius, the fuel piping system is maintained between -10 and 60 degrees Celsius, the hydraulic system's operating temperature is controlled between 40 and 80 degrees Celsius, and the suitable temperature range for the water pump system is 5 to 70 degrees Celsius. When a low-temperature activation signal is triggered, the system immediately retrieves these preset values ​​from the database as a reference for temperature adjustment.

[0084] Specifically, the temperature deviation is calculated using the difference between the current measured temperature and the boundary value of the target temperature range. When the current engine temperature is 65 degrees Celsius, there is a deviation of -15 degrees Celsius compared to the target lower limit of 80 degrees Celsius. When the fuel line temperature is -15 degrees Celsius, there is a deviation of -5 degrees Celsius relative to the lower limit of -10 degrees Celsius. The hydraulic system temperature of 30 degrees Celsius has a deviation of -10 degrees Celsius from the target lower limit of 40 degrees Celsius. This deviation quantification method can accurately reflect the degree to which each component deviates from its normal operating condition.

[0085] In one embodiment, the NumPy deviation matrix organizes temperature deviation data as a two-dimensional array. Rows represent different component types, and columns represent temperature deviation values ​​and deviation status indicators. Engine deviation matrix elements are [-15, 1], where -15 represents the deviation value and 1 indicates a temperature deviation threshold exceeding the set threshold. Fuel lines correspond to [-5, 1], hydraulic systems to [-10, 1], and water pump systems to [-8, 1]. When the absolute value of the deviation exceeds a preset 3-degree Celsius temperature deviation threshold, the status indicator is set to 1, triggering the subsequent adjustment strategy selection process.

[0086] Specifically, the decision tree algorithm matches the most suitable temperature regulation scheme from the regulation strategy database based on the characteristics of the deviation matrix. For an engine deviation of -15 degrees Celsius, the decision tree selects a strategy of increasing the preheating time to 8 minutes and increasing the idle speed to 1200 rpm. For a fuel line deviation of -5 degrees Celsius, the system activates the fuel heater for 15 minutes. A hydraulic system deviation of -10 degrees Celsius triggers the hydraulic oil preheating circulation mode, and a water pump deviation of -8 degrees Celsius initiates the water pump preheating program.

[0087] In one embodiment, the control command generation process translates the adjustment strategy into specific equipment operating parameters. Engine control commands include adjusting the throttle opening to 25%, setting the ignition advance angle to 8 degrees, and increasing the coolant circulation pump speed to 60% of its rated speed. Fuel system commands set the heater power to 800 watts for a heating duration of 15 minutes. Hydraulic system commands start the preheating pump at 200 rpm for a preheating time of 10 minutes.

[0088] It should be noted that the temperature monitoring after parameter adjustment uses continuous sampling to verify the adjustment effect. The system collects temperature data of each component every 30 seconds and calculates the new temperature deviation value. When the engine temperature rises to 78 degrees Celsius, the deviation from the target lower limit narrows to -2 degrees Celsius, which is within an acceptable range. If the fuel line temperature is still -12 degrees Celsius, the deviation is -2 degrees Celsius but still exceeds the temperature deviation threshold, the system will generate a new deviation matrix to continue optimizing the adjustment strategy, ensuring that all key components reach the appropriate operating temperature.

[0089] S3. If any element in the deviation matrix exceeds the preset deviation threshold, the elements of the deviation matrix are integrated through the proportional-integral-derivative control algorithm to generate a power adjustment command, thereby obtaining a dynamic power output sequence.

[0090] Optionally, this step also includes:

[0091] Step S31: If any element of the deviation matrix exceeds the preset deviation threshold, the excess element is extracted to generate deviation distribution data.

[0092] Step S32: The deviation distribution data is processed by the proportional-integral-derivative controller to calculate the power control parameters and obtain the power adjustment command.

[0093] Preferably, the power control parameters are calculated using the following formula:

[0094] ,

[0095] in, These are power control parameters. It is the proportionality coefficient. It is the difference between the biased distribution data and zero. It is the integral coefficient. yes Integral over time, These are differential coefficients. It is the derivative of e with respect to time.

[0096] Step S33: According to the power adjustment command, adjust the power output through the linear programming solver to generate the initial power output sequence.

[0097] Step S34: If there is a deviation between the initial power output sequence and the target output sequence, calculate the sequence deviation value to obtain the deviation correction data, where the sequence deviation value is the difference sequence between the initial power output sequence and the target output sequence.

[0098] Step S35: Smooth the bias correction data using a Kalman filter to generate an optimized power output sequence.

[0099] Preferably, the deviation correction data is calculated using the following formula:

[0100] ,

[0101] Where x is the bias correction data, x' is the prediction bias correction data, K is the Kalman gain, z is the measured value, and H is the measurement matrix.

[0102] Optionally, the prediction bias correction data x' can be calculated using the following formula:

[0103] x'=Fx+u

[0104] Where F is the state transition matrix and u is the power control parameter.

[0105] Step S36: Based on the optimized power output sequence, adjust the power distribution using a linear programming solver to obtain the final power output sequence.

[0106] Step S37: If the final power output sequence meets the preset performance threshold, then store the sequence data and generate a dynamic power control log.

[0107] In one embodiment, during the extraction of out-of-limit elements from the deviation matrix, when the engine fuel line temperature deviation is -8 degrees, the hydraulic system temperature deviation is +12 degrees, and the water pump temperature deviation is -15 degrees, if the preset deviation threshold is 10 degrees, the deviation values ​​of the hydraulic system and the water pump are identified as out-of-limit elements. The system organizes these out-of-limit data into a deviation distribution data structure, forming the basic input for subsequent control processing.

[0108] Specifically, when processing deviation distribution data, the proportional-integral-derivative controller sets a proportional coefficient. 0.8, integral coefficient The differential coefficient is 0.2. With a parameter combination of 0.1, dynamic response calculations are performed for temperature deviation. When the hydraulic system temperature deviation is 12 degrees, the proportional term contributes 9.6 units of control input, the integral term contributes 2.4 units of control input based on the accumulated historical deviation, and the derivative term contributes 1.2 units of control input based on the rate of change of deviation, ultimately generating a power adjustment command of 13.2 units. This polynomial control strategy can simultaneously consider fast response, steady-state accuracy, and system stability.

[0109] In one possible implementation, the linear programming solver receives a power adjustment command and optimizes the power allocation scheme under constraints. Assuming the engine heating power limit is 50 kW, the hydraulic system heating power limit is 30 kW, and the water pump heating power limit is 20 kW, the solver allocates power resources based on temperature deviation priority, generating an initial sequence containing the power output values ​​of each component.

[0110] For example, when the initial power output sequence is 35 kW for the engine, 25 kW for the hydraulic system, and 18 kW for the water pump, and the target output sequence is 40 kW for the engine, 20 kW for the hydraulic system, and 15 kW for the water pump, the sequence deviation values ​​are -5 kW, +5 kW, and +3 kW, respectively. These deviation correction data reflect the gap between the actual output and the expected output.

[0111] Specifically, the Kalman filter processes bias correction data through two stages: state prediction and measurement update. In the state prediction stage, the filter predicts the bias state at the next moment based on the system dynamic model. In the measurement update stage, it corrects the prediction result by incorporating actual measured temperature feedback. Through this recursive estimation process, the filter can effectively suppress measurement noise and system disturbances, generating a smooth and stable optimized power output sequence.

[0112] In one embodiment, the optimized power output sequence is adjusted using quadratic linear programming to ensure that the power distribution meets both temperature control requirements and system energy consumption constraints. Once the final power output sequence meets preset performance thresholds, the system automatically records key data such as control parameters, power allocation schemes, and temperature response curves, forming a complete dynamic power control log. This closed-loop control mechanism enables precise temperature regulation and improves the operational reliability of components in low-temperature environments.

[0113] S4 uses a dynamic power output sequence to drive multiple heaters to heat the engine block and fuel lines in parallel, while monitoring the rate of temperature change during the heating process to determine the degree of heating uniformity.

[0114] Optionally, this step also includes:

[0115] Step S41: Obtain the dynamic power sequence of the multi-channel heaters and determine the initial power output using a linear programming solver.

[0116] Step S42: Drive the multi-channel heater according to the initial power output to perform parallel heating on the engine block and fuel line to obtain the first temperature data.

[0117] Step S43: Extract the temperature change rate from the first temperature data, and determine the temperature change trend of each heating zone through differential calculation.

[0118] Step S44: If the temperature change trend shows that the rate of change in a certain area exceeds the preset temperature change rate threshold, then adjust the first power sequence of the heater in that area to obtain the second power output.

[0119] Step S45: Re-drive the multi-channel heaters according to the second power output to obtain the second temperature data.

[0120] Step S46: Calculate the heating uniformity of each region from the second temperature data using the standard deviation formula, where the standard deviation is the square root of the temperature variance of each region, and the temperature is a value in degrees Celsius.

[0121] Step S47: Determine whether to continue adjusting the first power sequence by comparing the heating uniformity with the preset first uniformity threshold.

[0122] Step S48: If the heating uniformity does not reach the preset first uniformity threshold, return to the temperature change rate extraction operation and iterate until the heating uniformity meets the requirements.

[0123] In one embodiment, the dynamic power sequence of the multi-channel heater is acquired and configured based on the actual needs of the engine preheating system.

[0124] Specifically, when the engine is in a cold start state, the cylinder block temperature is typically between -15 degrees Celsius and 5 degrees Celsius, and the fuel line temperature may be even lower. The linear programming solver will allocate 60% of the total power to the cylinder block heater and 40% of the power to the fuel line heater based on the initial temperature differences in each region, forming an initial power allocation scheme.

[0125] For example, during the initial temperature data acquisition, the temperature sensor monitors each heating zone five times per second. The temperature in the cylinder block front area starts to rise from -10 degrees Celsius, while the fuel line inlet section starts heating from -18 degrees Celsius. When extracting the temperature change rate through differential calculation, the system calculates the temperature difference between adjacent time points divided by the time interval. When the temperature change rate of a certain area exceeds a preset threshold of 8 degrees Celsius per minute, it indicates that the area is heating too rapidly, which may lead to thermal stress concentration.

[0126] In one possible implementation, the power sequence adjustment mechanism employs a segmented control strategy. If the temperature rise rate in the middle section of the cylinder reaches 12 degrees Celsius per minute, exceeding a preset first equalization threshold, the system will reduce the heater power in that area from the original 800 watts to 600 watts, generating a second power output. Simultaneously, to maintain overall heating efficiency, the system will redistribute the saved 200 watts of power to areas where the temperature rises more slowly.

[0127] It should be noted that the heating evenness calculation achieves precise control through a standard deviation formula. When the temperatures of each heating zone are 25°C, 28°C, 23°C, and 27°C respectively, the average temperature is 25.75°C, and the calculated standard deviation is approximately 2.1°C. If the preset first evenness threshold is 1.5°C, the current state does not meet the requirements, and the power distribution needs to be further adjusted.

[0128] For example, during the iterative optimization process, the system continuously monitors temperature trends. When the standard deviation gradually decreases from the initial 3.2 degrees Celsius to 1.8 degrees Celsius and then to 1.4 degrees Celsius, it indicates that the temperature in each region is becoming more balanced. This process typically requires 3 to 5 iterations, with each iteration spaced approximately 30 seconds apart, to ensure the stability and reliability of the temperature data.

[0129] In one embodiment, the parallel heating control strategy can significantly improve preheating efficiency. Through real-time monitoring and dynamic adjustment, the system can avoid localized overheating and extend heater lifespan. Simultaneously, a balanced temperature distribution helps reduce internal engine thermal stress and improves start-up reliability. When the temperature in all areas reaches the preset target range and the heating uniformity meets requirements, the system maintains the current power configuration, achieving a stable temperature maintenance state.

[0130] S5 obtains real-time updated data from the temperature sensors of the hydraulic system and water pump based on the heating uniformity. If the rate of change is lower than the preset rate threshold, the power distribution ratio is adjusted to determine the optimized heating path.

[0131] Optionally, this step also includes:

[0132] Step S51: Obtain real-time data from the temperature sensors of the hydraulic system and water pump.

[0133] Step S52: Calculate the time-series temperature values ​​of each sensor, where the time-series temperature values ​​are the reading sequences of the sensors at different time points.

[0134] Step S53: Calculate the real-time heating uniformity based on the time series temperature values.

[0135] Preferably, the real-time heating uniformity is calculated using the following formula:

[0136] ,

[0137] Where E is the real-time heating uniformity, T is the temperature value sequence, max(T) is the maximum temperature, min(T) is the minimum temperature, and avg(T) is the average temperature.

[0138] Step S54: If the real-time heating uniformity is lower than the preset second uniformity threshold, the temperature data is clustered using the K-means algorithm of scikit-learn. First, the temperature data is standardized, and then the number of clusters is set to 3. After clustering, the cluster with the lowest temperature is determined as the abnormal region, and the distribution of abnormal regions is obtained.

[0139] Step S55: Based on the distribution of abnormal areas, calculate the rate of temperature change for each area using the formula R=(T_t-T_{t-1}) / Δt, where R is the rate of change, T_t is the current temperature, T_{t-1} is the previous temperature, and Δt is the time interval.

[0140] Preferably, the rate of temperature change is calculated using the following formula:

[0141] ,

[0142] Where R is the rate of temperature change. This is the current temperature. Δt represents the temperature at the previous time, and Δt represents the time interval.

[0143] Step S56: Determine whether the rate of change is lower than a preset rate threshold to obtain the rate abnormality region.

[0144] Step S57: If there is an abnormal rate region, the power adjustment magnitude is predicted by the linear regression algorithm of scikit-learn. First, historical data of temperature and power in the abnormal region are fitted, and then the required magnitude is predicted to determine the power allocation ratio.

[0145] Step S58: Adjust the power distribution of the hydraulic system and water pump according to the power distribution ratio, and generate new control commands.

[0146] Step S59: Obtain new real-time data from the temperature sensor, calculate the updated real-time heating uniformity, determine whether the preset second uniformity threshold has been reached, and obtain the system operating status.

[0147] In one embodiment, acquiring temperature sensor data for the hydraulic system and water pump requires establishing a complete monitoring network.

[0148] Specifically, hydraulic systems typically place temperature sensors at key locations such as the oil tank, main pump, return oil filter, and actuators, while water pump systems have monitoring points at the inlet, outlet, bearing chamber, and sealing cavity. The sensor sampling frequency is set to 10 times per second to ensure the capture of rapid temperature changes. The time-series temperature values ​​form a continuous data stream; for example, a 5-minute temperature reading sequence from the hydraulic oil tank might consist of 300 data points, such as 45.2℃, 45.8℃, 46.1℃, and 46.5℃.

[0149] For example, in real-time heating uniformity calculation, when the temperatures at various monitoring points in the hydraulic system are 48℃, 52℃, 46℃, and 50℃ respectively, with a maximum temperature of 52℃, a minimum temperature of 46℃, and an average temperature of 49℃, the uniformity E = 1 - (52 - 46) / 49 = 0.878. When this value is lower than the preset second uniformity threshold of 0.9, the system determines that there is a heating unevenness problem. At this time, it is necessary to identify abnormal areas using the K-means clustering algorithm. After standardizing the temperature data, it is divided into three clusters: high temperature, medium temperature, and low temperature. The monitoring points contained in the low temperature cluster are the abnormal areas that need to be focused on.

[0150] In one possible implementation, the temperature change rate calculation can reflect the heating response characteristics of each region. For example, if the temperature of a hydraulic actuator rises from 42℃ to 44℃ in 30 seconds, the change rate is 0.067℃ / second. When this change rate is lower than a preset threshold of 0.1℃ / second, it indicates that the heating efficiency of that region is insufficient, and power allocation needs to be adjusted. A linear regression algorithm establishes a predictive model by analyzing the relationship between temperature and power in historical data. Assuming that historical data for a certain region shows that every 100W increase in power corresponds to a 0.02℃ / second increase in temperature rise rate, then if a current increase of 0.033℃ / second is needed, it is predicted that an additional 165W of power is required.

[0151] Specifically, power allocation adjustments are dynamically optimized based on the actual needs of each area. The original power allocation might be: 800W for the main hydraulic pump, 600W for the auxiliary pump, 1000W for the main water pump, and 400W for the circulating pump. Based on predictions, power needs to be increased in abnormal areas, while power in normal areas can be appropriately reduced to maintain overall power balance. The adjusted new control commands are sent to each power control unit via CAN bus or industrial Ethernet to achieve precise power regulation.

[0152] It should be noted that determining the system's operating status requires comprehensive consideration of both the real-time heating uniformity and system stability. When the updated real-time heating uniformity reaches 0.92, exceeding the preset second uniformity threshold of 0.9, the system is considered to be in normal operating condition. This closed-loop control method enables adaptive optimization of temperature distribution, significantly improving the overall performance and reliability of the heating system while reducing energy consumption and equipment wear.

[0153] S6, the auxiliary heating module is activated synchronously through the optimized heating path to circulate and preheat the fluid inside the water pump. The overall system temperature coordination index is calculated in combination with the updated version of the deviation matrix to obtain the coordination completion indicator.

[0154] Optionally, this step also includes:

[0155] Step S61: Solve the heating path using PuLP linear programming to generate an initial heating scheme.

[0156] Step S62: Activate the auxiliary heating module from the initial heating scheme, obtain the module's operating status, and determine the fluid preheating starting temperature.

[0157] Step S63: If the module is running stably, perform a circulating preheating process on the fluid inside the water pump to obtain the fluid circulation efficiency and determine the uniformity of temperature distribution.

[0158] Step S64: Based on the fluid circulation efficiency, the heating path planning is adjusted by generating a deviation matrix using a NumPy array to obtain the adjusted heating scheme.

[0159] Step S65: If the adjusted heating scheme meets the preset temperature distribution uniformity threshold, then calculate the temperature synergy index through the deviation matrix and obtain the synergy index value.

[0160] Preferably, the synergy index value is calculated using the following formula:

[0161] ,

[0162] Where C is the temperature co-existence index. denoted as elements of the deviation matrix, and N is the total number of elements.

[0163] Step S66: The collaboration index value is compared with the preset collaboration threshold to determine the collaboration status and obtain the collaboration completion flag.

[0164] Step S67: Through collaborative completion of flag update operation parameters, obtain the optimized fluid circulation efficiency and determine the final temperature distribution state.

[0165] Step S68: Adjust the operating frequency of the auxiliary heating module according to the final temperature distribution state to obtain a stable operating configuration.

[0166] In one embodiment, the PuLP linear programming solver generates an initial heating scheme by establishing an objective function and constraints.

[0167] Specifically, the system sets the heating requirements of the hydraulic system and water pump as the optimization target, while taking into account conditions such as power limits, temperature limits and time constraints.

[0168] For example, when the hydraulic system needs to be heated from 15 degrees Celsius to 45 degrees Celsius, and the water pump needs to be heated from 20 degrees Celsius to 40 degrees Celsius, the linear programming algorithm will calculate the optimal power allocation strategy to ensure that the total energy consumption is minimized while meeting the heating time requirements.

[0169] For example, after the auxiliary heating module is activated, it will perform a self-test program, monitoring the resistance value of the heating element, the response time of the temperature controller, and the status of the safety protection devices. When the module's operating status shows as stable, the system begins to determine the fluid preheating starting temperature.

[0170] In one possible implementation, the initial temperature distribution of the fluid is obtained through multi-point temperature sampling, and the average value is calculated as the preheating starting point benchmark. If the initial temperature of the hydraulic oil is 18 degrees Celsius and the coolant is 22 degrees Celsius, the system will formulate a preheating strategy based on the lower temperature.

[0171] Specifically, the internal fluid circulation preheating process of the water pump achieves temperature uniformity by controlling the pump speed and flow rate. Fluid circulation efficiency is evaluated by monitoring the inlet and outlet temperature difference and flow rate changes; when the temperature difference gradually decreases and the flow rate remains stable, it indicates good circulation efficiency.

[0172] For example, if the initial temperature difference between the inlet and outlet is 8 degrees Celsius, it drops to less than 2 degrees Celsius after circulating preheating, indicating that the temperature distribution tends to be uniform.

[0173] In one embodiment, a deviation matrix generated by a NumPy array records the difference between the temperature at each measuring point and the target temperature. Positive values ​​in the matrix represent areas with higher temperatures, and negative values ​​represent areas with lower temperatures. The system adjusts the heating power distribution based on the deviation distribution, increasing the heating intensity in areas with lower temperatures and reducing the power output in areas with higher temperatures. This dynamic adjustment mechanism can effectively improve the uniformity of temperature distribution.

[0174] For example, when the temperature distribution uniformity threshold is set to 95%, the system checks whether the temperature at each measuring point is within 5% of the target temperature. If the condition is met, a temperature coordination index is calculated to assess the overall coordination level. The closer the coordination index value is to zero, the more coordinated the temperatures of each area are.

[0175] It should be noted that the determination of the coordination completion indicator is based on the comparison between the coordination index and the preset coordination threshold. When the coordination index is lower than the coordination threshold, the system considers the temperature coordination to have met the requirements and updates the operating parameters to maintain the current state. The optimized fluid circulation efficiency is typically 15% to 25% higher than the initial state, significantly improving the system's heat exchange performance.

[0176] Specifically, determining the final temperature distribution requires comprehensive consideration of the temperature stability and variation trends in each region. The system maintains a stable operating configuration by adjusting the operating frequency of the auxiliary heating modules, ensuring that the temperature distribution remains uniform and stable during long-term operation.

[0177] S7: Obtain the start-up preparation signal from the vehicle control unit based on the coordination completion flag. If the temperature coordination index reaches the preset index threshold, release the start-up sequence and determine the vehicle's responsiveness.

[0178] Optionally, this step also includes:

[0179] Step S71: Obtain the coordination completion flag and start preparation signal from the vehicle control unit, process the obtained signal data using json.loads, and obtain the first signal status.

[0180] Step S72: If the first signal state is true, obtain the temperature co-index from the environmental sensor, and use sklearn's StandardScaler to standardize the temperature co-index to obtain the standardized temperature index.

[0181] Step S73: Compare the standardized temperature index with a preset index threshold. If the standardized temperature index reaches the preset index threshold, generate a start sequence release command.

[0182] Step S74: The start sequence release of the vehicle control unit is triggered by the start sequence release command, and the release status is determined according to the start sequence release.

[0183] Step S75: Obtain real-time response data of the vehicle power system based on the release status, use NumPy to calculate the mean and variance of the real-time response data, and determine the first response capability.

[0184] Step S76: If the first response capability meets the preset response conditions, a response capability confirmation signal is generated, and the response capability confirmation signal is sent using a socket to obtain the first response result.

[0185] Step S77: Update the status record of the vehicle control unit according to the first response result, and use sqlite to insert the first response result to obtain the updated data of the vehicle operating status.

[0186] In one embodiment, when the vehicle control unit receives a coordination completion flag via the CAN bus, this flag is typically in hexadecimal format: 0x01 indicates readiness for startup, and 0x00 indicates incomplete readiness. The json.loads process converts the raw string data into operable Boolean values, ensuring accurate identification of the first signal state. When the first signal state is true, the system immediately activates the environmental sensor array, including the cabin temperature sensor, the engine compartment temperature monitor, and the battery pack thermal management sensor.

[0187] Specifically, StandardScaler's normalization process converts the original temperature coordination index into a standardized value with a mean of 0 and a standard deviation of 1. Assuming the original temperature coordination index is 85.6, the normalized temperature index is 1.23. The preset index threshold is typically set to 1.0; when the normalized temperature index exceeds this threshold, it indicates that the temperature monitoring points have reached a state of coordination.

[0188] For example, the start sequence release command uses a specific data frame format, including a timestamp, priority identifier, and execution parameters. This command is sent to the vehicle control unit via a high-priority channel, triggering the coordinated start-up of the ignition system, fuel injection system, and motor controller. Release status monitoring covers the response time and execution completion rate of each subsystem; under normal circumstances, the entire release process is completed within 200 milliseconds.

[0189] In one possible implementation, the real-time response data of the vehicle powertrain includes torque output, rate of change of speed, and power distribution ratio. During the NumPy calculation, assuming 100 data points are collected, the calculated mean is 156.8 Nm and the variance is 12.4. The initial response capability assessment is based on preset response conditions: a response time of less than 150 milliseconds and torque fluctuation within ±5%.

[0190] It should be noted that socket communication uses the TCP protocol to ensure the reliable transmission of the response capability confirmation signal. This signal includes the response capability level, timestamp, and verification code. The receiving end confirms the signal integrity through a verification mechanism. The first response result reflects the degree of coordination of the entire power system, including the synchronization of each actuator and the stability of the output.

[0191] Specifically, SQLite database insert operations store the initial response as a structured record, containing fields such as response time, execution status, and performance parameters. Updated data provides historical references for subsequent system optimization and fault diagnosis, while also supporting real-time monitoring and predictive maintenance of vehicle operating status. This data-driven status management approach significantly improves the reliability and response accuracy of the vehicle control system.

[0192] like Figure 4As shown, in a second aspect, the present invention provides an adaptive starting system for fire trucks in low-temperature environments. The system employs the method described above to enable adaptive starting of fire trucks in low-temperature environments. The system mainly includes: a temperature monitoring module, used to acquire real-time temperature data from the environment and key components of the fire truck via a sensor array, and to determine whether the vehicle is in a low-temperature state based on a threshold comparison method according to the collected temperature distribution, thereby obtaining a low-temperature activation signal; a temperature demand analysis module, used to obtain the target temperature ranges for the engine fuel line hydraulic system and water pump from a preset temperature demand model based on the low-temperature activation signal, and to calculate the deviation between the current temperature and the target temperature using a linear interpolation algorithm to determine the deviation matrix; and a power control module, used to generate a power adjustment command by integrating the elements of the deviation matrix using a proportional-integral-derivative control algorithm if any element in the deviation matrix exceeds a preset deviation threshold, thereby obtaining a dynamic power... The system comprises the following modules: a power output sequence; a heating execution module, used to drive multiple heaters to heat the engine block and fuel lines in parallel using a dynamic power output sequence, while monitoring the rate of temperature change during heating and determining the heating balance; a balance monitoring module, used to obtain real-time updated data from temperature sensors in the hydraulic system and water pump based on the heating balance, and if the rate of change is lower than a preset rate threshold, adjusting the power distribution ratio to determine an optimized heating path; a path optimization module, used to synchronously activate the auxiliary heating module to circulate and preheat the fluid inside the water pump through the optimized heating path, and calculate the overall system temperature coordination index based on the updated version of the deviation matrix to obtain a coordination completion flag; and a coordination start module, used to obtain a start preparation signal from the vehicle control unit based on the coordination completion flag, and if the temperature coordination index reaches a preset index threshold, releasing the start sequence and determining the vehicle's responsiveness. The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the technical scope disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for adaptive starting of fire trucks in low-temperature environments, characterized in that, The method includes: S1. Real-time temperature data is acquired from the environment and key components of the fire truck using a sensor array. A threshold comparison method is used to determine if the system is in a low-temperature state based on the collected temperature distribution, generating a low-temperature activation signal. S2. Based on the low-temperature activation signal, the target temperature ranges for the engine fuel line hydraulic system and water pump are obtained from a preset temperature demand model. The deviation between the current temperature and the target temperature is calculated, and a deviation matrix is ​​determined. S3. If any element in the deviation matrix exceeds a preset deviation threshold, the elements of the deviation matrix are integrated to generate a power adjustment command, resulting in a dynamic power output sequence. S4. The dynamic power output sequence is used to drive multiple heaters to heat the engine block and fuel lines in parallel. Simultaneously monitor the temperature change rate during the heating process to determine the heating uniformity; S5, obtain real-time updated data from the temperature sensors of the hydraulic system and water pump based on the heating uniformity. If the change rate is lower than the preset rate threshold, adjust the power distribution ratio and determine the optimized heating path; S6, synchronously activate the auxiliary heating module through the optimized heating path to circulate and preheat the fluid inside the water pump. Combine the updated version of the deviation matrix to calculate the overall system temperature coordination index and obtain the coordination completion flag; S7, obtain the start-up preparation signal from the vehicle control unit based on the coordination completion flag. If the temperature coordination index reaches the preset index threshold, release the start-up sequence and determine the vehicle's response capability.

2. The adaptive starting method for fire trucks in low-temperature environments according to claim 1, characterized in that, In step S3, if any element in the deviation matrix exceeds a preset deviation threshold, the elements of the deviation matrix are integrated to generate a power adjustment command, resulting in a dynamic power output sequence, including: Step S31: If any element of the deviation matrix exceeds the preset deviation threshold, the excess element is extracted to generate deviation distribution data. Step S32: Process the deviation distribution data through a proportional-integral-derivative controller, calculate the power control parameters, and obtain the power adjustment command; Step S33: Adjust the power output according to the power adjustment command to generate an initial power output sequence; Step S34: If there is a deviation between the initial power output sequence and the target output sequence, calculate the sequence deviation value and obtain the deviation correction data; Step S35: Smooth the deviation correction data to generate an optimized power output sequence; Step S36: Adjust the power distribution according to the optimized power output sequence to obtain the final power output sequence; Step S37: If the final power output sequence meets the preset performance threshold, then store the sequence data and generate a dynamic power control log.

3. The adaptive starting method for fire trucks in low-temperature environments according to claim 2, characterized in that, Step S32 involves processing the deviation distribution data using a proportional-integral-derivative controller, calculating power control parameters, and obtaining a power adjustment command, including: Calculate the power control parameters using the following formula: ， in, These are power control parameters. It is the proportionality coefficient. It is the difference between the biased distribution data and zero. It is the integral coefficient. yes Integral over time, These are differential coefficients. It is the derivative of e with respect to time.

4. The adaptive starting method for fire trucks in low-temperature environments according to claim 3, characterized in that, In step S34, if there is a deviation between the initial power output sequence and the target output sequence, the sequence deviation value is calculated to obtain deviation correction data, including: the sequence deviation value is the difference sequence between the initial power output sequence and the target output sequence.

5. The adaptive starting method for fire trucks in low-temperature environments according to claim 4, characterized in that, Step S35 involves smoothing the deviation correction data to generate an optimized power output sequence, including: Calculate the deviation correction data using the following formula: , Wherein, the state vector x is the bias correction data, x' is the prediction bias correction data, K is the Kalman gain, z is the measurement value, and H is the measurement matrix.

6. The adaptive starting method for fire trucks in low-temperature environments according to claim 5, characterized in that, The prediction bias correction data are calculated using the following formula: x'=Fx+u Where F is the state transition matrix and u is the power control parameter.

7. The adaptive starting method for fire trucks in low-temperature environments according to claim 1, characterized in that, Step S5 involves obtaining real-time updated data from the temperature sensors of the hydraulic system and water pump based on the heating uniformity. If the rate of change is lower than a preset rate threshold, the power distribution ratio is adjusted to determine the optimized heating path, including: Step S51: Obtain real-time data from the temperature sensors of the hydraulic system and water pump; Step S52: Calculate the time-series temperature values ​​of each sensor, where the time-series temperature values ​​are the reading sequences of the sensors at different time points; Step S53: Calculate the real-time heating uniformity based on the time series temperature values; Step S54: If the real-time heating uniformity is lower than the preset second uniformity threshold, then the temperature data is clustered. First, the temperature data is standardized, then the number of clusters is set to 3. After clustering, the cluster with the lowest temperature is determined as the abnormal region, and the distribution of abnormal regions is obtained. Step S55: Calculate the rate of temperature change in each region based on the distribution of abnormal regions; Step S56: Determine whether the rate of change is lower than a preset rate threshold to obtain the rate abnormality region; Step S57: If there is a rate anomaly region, predict the power adjustment range and determine the power allocation ratio. Step S58: Adjust the power distribution of the hydraulic system and water pump according to the power distribution ratio, and generate new control commands; Step S59: Obtain new real-time data from the temperature sensor, calculate the updated real-time heating uniformity, determine whether the preset second uniformity threshold has been reached, and obtain the system operating status.

8. The adaptive starting method for fire trucks in low-temperature environments according to claim 7, characterized in that, Step S53, which calculates the real-time heating uniformity based on the time-series temperature values, includes: Calculate real-time heating uniformity using the following formula: , Where E is the real-time heating uniformity, T is the temperature value sequence, max(T) is the maximum temperature, min(T) is the minimum temperature, and avg(T) is the average temperature.

9. The adaptive starting method for fire trucks in low-temperature environments according to claim 8, characterized in that, Step S55, based on the distribution of abnormal areas, calculates the rate of temperature change in each area, including: Calculate the rate of temperature change using the following formula: , Where R is the rate of temperature change. This is the current temperature. Δt represents the temperature at the previous time, and Δt represents the time interval.

10. An adaptive starting system for fire trucks in low-temperature environments, characterized in that, The system employs the method described in any one of claims 1-9 to adaptively start fire trucks in low-temperature environments. The system comprises: a temperature monitoring module, used to acquire real-time temperature data from the environment and key components of the fire truck via a sensor array, and to determine whether the vehicle is in a low-temperature state based on a threshold comparison method according to the collected temperature distribution, thereby obtaining a low-temperature activation signal; a temperature demand analysis module, used to obtain the target temperature ranges for the engine fuel line hydraulic system and water pump from a preset temperature demand model based on the low-temperature activation signal, and to calculate the deviation between the current temperature and the target temperature using an algorithm to determine a deviation matrix; a power control module, used to integrate the elements of the deviation matrix to generate a power adjustment command if any element in the deviation matrix exceeds a preset deviation threshold, thereby obtaining a dynamic power output sequence; and a heating execution module, used to apply the dynamic power output... A sequence-driven multi-channel heater performs parallel heating of the engine block and fuel lines, while monitoring the rate of temperature change during the heating process to determine the heating uniformity. A uniformity monitoring module obtains real-time updated data from temperature sensors in the hydraulic system and water pump based on the heating uniformity. If the rate of change is lower than a preset threshold, the power distribution ratio is adjusted to determine an optimized heating path. A path optimization module synchronously activates an auxiliary heating module to circulate and preheat the fluid inside the water pump using the optimized heating path. It calculates the overall system temperature coordination index based on the updated version of the deviation matrix to obtain a coordination completion flag. A coordination start module obtains a start-up preparation signal from the vehicle control unit based on the coordination completion flag. If the temperature coordination index reaches a preset threshold, the start sequence is released to assess the vehicle's responsiveness.

Images