Energy-saving control system and method for chassis of truck crane

Abstract

The application discloses a kind of automobile crane chassis energy-saving control system and method, belong to crane technical field, this control system includes: perception module, data processing module and control module, wherein: perception module is used to detect the torque variation data in the power transmission process of automobile crane and the pressure data of each part of hydraulic system;Data processing module is used to receive the torque variation data and pressure data detected by perception module, filtering and normalization processing are carried out;Control module is connected with data processing module, control module can call energy consumption prediction model with the filtered and normalized data as input, with the energy consumption prediction data of automobile crane as output, to predict the energy consumption of automobile crane, and dynamically adjust the electrical system and hydraulic system of automobile crane chassis according to the predicted result.By the application, closed-loop control can be carried out on the chassis of automobile crane, and the problem of excessive or insufficient adjustment in the prior art can be avoided.

Description

Technical Field

[0001] This invention relates to the field of crane technology, and in particular to an energy-saving control system and method for a truck crane chassis. Background Technology

[0002] As core equipment in infrastructure construction, the energy consumption management of the chassis electrical system of truck cranes is a key aspect of achieving green development. However, current truck crane chassis electrical systems still have significant shortcomings in terms of energy efficiency and intelligent collaborative control.

[0003] Traditional truck crane chassis electrical control systems employ a crude energy management model. In the power transmission stage, the matching between the engine and the electric hydraulic pump lacks an intelligent adjustment mechanism, making it difficult for the engine to maintain efficient operation under different working conditions. For example, during unloaded travel or light-load operation, the engine maintains high speed, resulting in significant redundancy of electrical energy generated by the power generation system and ineffective energy consumption. Under heavy-load conditions, insufficient power output may lead to frequent speed reductions, further exacerbating energy consumption. Furthermore, at the intelligent control level, existing chassis electrical systems lack coordinated control mechanisms among their various sub-modules (such as steering, braking, and driving systems). Each system operates independently, unable to dynamically adjust power distribution according to actual working conditions, resulting in persistently high overall energy consumption. For instance, traditional electric power steering systems consume a large amount of electrical energy during steering, and steering accuracy relies on fixed control parameters, making precise energy-saving control difficult. The chassis driving system also cannot adaptively adjust motor speed and torque through electrical control under different road conditions, leading to energy waste. Summary of the Invention

[0004] To address some or all of the technical problems existing in the prior art, this invention provides an energy-saving control system and method for a truck crane chassis. This system enables closed-loop control of the truck crane chassis and allows for precise dynamic adjustment of the electrical and hydraulic systems of the truck crane chassis based on accurate predictions. This ensures the timeliness and accuracy of the dynamic adjustment of the truck crane chassis and solves the problem of "over-adjustment or under-adjustment" caused by data errors in the prior art.

[0005] The technical solution of the present invention is as follows:

[0006] In a first aspect, an energy-saving control system for a truck crane chassis is provided, comprising:

[0007] The sensing module is used to detect torque change data and pressure data of various parts of the hydraulic system of the truck crane during the power transmission process.

[0008] A data processing module, connected to the sensing module, is used to receive torque change data and pressure data detected by the sensing module, and perform filtering and normalization processing.

[0009] The control module is connected to the data processing module. The control module can call an energy consumption prediction model that takes filtered and normalized data as input and energy consumption prediction data of the truck crane as output to predict the energy consumption of the truck crane, and dynamically adjust the electrical and hydraulic systems of the truck crane chassis according to the prediction results.

[0010] Furthermore, in the aforementioned energy-saving control system for a truck crane chassis, the sensing module includes a torque detection device, which is located at the connection between the engine and the transmission system of the truck crane.

[0011] Furthermore, in the aforementioned energy-saving control system for a truck crane chassis, the torque detection device includes a torque sensor.

[0012] Furthermore, in the aforementioned energy-saving control system for a truck crane chassis, the sensing module further includes pressure detection devices, and the number of pressure detection devices includes multiple devices, which are installed at hydraulic pipeline nodes of the truck crane.

[0013] Furthermore, in the aforementioned energy-saving control system for a truck crane chassis, the pressure detection device includes a pressure sensor.

[0014] Furthermore, the aforementioned energy-saving control system for a truck crane chassis also includes a low-voltage battery, which is electrically connected to the control module to provide electrical energy.

[0015] Secondly, an energy-saving control method for a truck crane chassis is provided, including:

[0016] Detect torque variation data and pressure data of various parts of the hydraulic system of the truck crane during the power transmission process;

[0017] The received torque and pressure data are preprocessed.

[0018] Using the preprocessed data after training as input data, an energy consumption prediction model is constructed using a long short-term memory network;

[0019] The energy consumption of the truck crane is predicted using the constructed energy consumption prediction model, and the electrical and hydraulic systems of the truck crane chassis are dynamically adjusted based on the prediction results.

[0020] Furthermore, in the aforementioned energy-saving control method for a truck crane chassis, the received torque change data and pressure data are preprocessed, including filtering and normalization.

[0021] Furthermore, in the aforementioned energy-saving control method for truck crane chassis, the energy consumption prediction model is constructed using pre-processed data after training as input data and a long short-term memory network, including:

[0022] During the training process, the Long Short-Term Memory (LSTM) network is iteratively trained using historical operating data of the vehicle. The backpropagation algorithm is used to adjust the weight parameters of the LSM network, enabling the energy consumption prediction model to accurately learn the energy consumption variation patterns under different operating conditions. The energy consumption prediction data of the truck crane is used as the output.

[0023] Furthermore, in the aforementioned energy-saving control method for a truck crane chassis, the historical operating data includes: vehicle speed, engine speed, hydraulic pipeline pressure, load weight, and energy consumption data.

[0024] The main advantages of the technical solution of this invention are as follows:

[0025] This invention discloses an energy-saving control system for a truck crane chassis. Through closed-loop control involving sensing by a sensing module, filtering and normalization by a data processing module, and prediction and adjustment by a control module, the control system no longer operates independently but rather coordinates actions based on global energy consumption prediction results. This reduces the overall energy consumption of the truck crane chassis by 15%-20% compared to existing systems, solving the problem of "high energy consumption due to independent operation" in existing technologies. Specifically, the filtering process of the data processing module effectively suppresses interference in sensor signals, and the normalization process eliminates differences in data scales from different sensors, reducing the input data error of the energy consumption prediction model by more than 30%. Precise data prediction enables the energy consumption prediction model to accurately predict the energy consumption of the truck crane, allowing for precise dynamic adjustment of the electrical and hydraulic systems of the truck crane chassis based on accurate predictions. This ensures the timeliness and accuracy of dynamic adjustment, avoiding the "over- or under-adjustment" problems caused by data errors in traditional systems. Attached Figure Description

[0026] The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and constitute a part of this invention, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0027] Figure 1 This is a schematic diagram illustrating the working principle of an energy-saving control system for a truck crane chassis, provided in one embodiment of the present invention.

[0028] Figure 2 A schematic diagram of low-voltage battery control in an energy-saving control system for a truck crane chassis, provided in an embodiment of the present invention;

[0029] Figure 3 This is a flowchart illustrating an energy-saving control method for a truck crane chassis according to an embodiment of the present invention.

[0030] Explanation of reference numerals in the attached figures:

[0031] 1. Sensing module; 2. Data processing module; 3. Control module; 4. Low-voltage battery. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0033] The following is in conjunction with the appendix Figure 1 - Appendix Figure 3 The technical solutions provided in the embodiments of the present invention will be described in detail.

[0034] As attached Figure 1 As shown, this embodiment of the invention provides an energy-saving control system for a truck crane chassis. The system includes: a sensing module 1, a data processing module 2, and a control module 3, wherein:

[0035] The sensing module 1 is used to detect torque change data and pressure data of various parts of the hydraulic system of the truck crane during the power transmission process. The data processing module 2 is connected to the sensing module 1 and is used to receive the torque change data and pressure data detected by the sensing module 1, and perform filtering and normalization processing. The control module 3 is connected to the data processing module 2. The control module 3 can call the energy consumption prediction model with the filtered and normalized data as input and the energy consumption prediction data of the truck crane as output to predict the energy consumption of the truck crane, and dynamically adjust the electrical system and hydraulic system of the truck crane chassis according to the prediction results.

[0036] Therefore, the energy-saving control system for a truck crane chassis of the present invention effectively suppresses interference in the sensing signals acquired by the sensing modules (such as torque data fluctuations caused by engine vibration) through filtering algorithms, and eliminates the scale differences of data from different sensing modules through normalization processing (such as unifying the dimensions of torque unit N·m and pressure unit MPa), reducing the input data error of the energy consumption prediction model by more than 30%. Furthermore, the high-quality data after filtering and normalization processing in the embodiments of the present invention supports the LSTM model to more accurately learn the correlation pattern between working conditions and energy consumption (such as the nonlinear relationship between torque-pressure-energy consumption during heavy-load lifting), which can reduce the energy consumption prediction error to within 5%, ensuring the timeliness and accuracy of dynamic adjustment, and avoiding the problem of "over- or under-adjustment" caused by data errors.

[0037] In some optional implementations of this embodiment, the sensing module includes a torque detection device and a pressure detection device. The torque detection device is located at the connection between the engine and the transmission system of the truck crane. The number of pressure detection devices includes multiple devices, which are located at hydraulic pipeline nodes of the truck crane.

[0038] Preferably, the torque detection device includes a torque sensor.

[0039] In some optional implementations of this invention, pressure sensors can be installed as connection points between pipelines. For example, a high-precision torque sensor with high measurement accuracy and a fast sampling frequency is installed at the connection between the engine and the transmission system, thus enabling real-time and accurate monitoring of torque changes during power transmission; pressure sensors are distributed at key nodes of the hydraulic pipeline. Preferably, to ensure more accurate pressure detection and adaptability to different operating temperatures, the operating temperature range of the pressure sensor is preferably set to -40°C to 120°C. This ensures the accuracy of the pressure data collected from various parts of the hydraulic system, providing a basis for adjusting the operating state of the hydraulic system.

[0040] In another optional implementation of this embodiment, the engine or motor provides the chassis driving speed information in real time, providing basic data for the system to judge the vehicle driving condition. Combined with the data collected by the pressure sensor and the high-precision torque sensor, the data is transmitted quickly and stably to the data processing module 2 at a transmission rate of 250kbps via a high-speed communication bus for corresponding data processing.

[0041] In some optional implementations of this embodiment, the data processing module 2 includes a high-performance computing unit capable of rapidly processing the data transmitted by the sensing module 1. Upon receiving the data detected and sensed by the sensing module 1, the data processing module 2 first performs filtering and normalization preprocessing. The filtering operation includes using filtering algorithms to remove noise from the sensor signals, ensuring data accuracy; and normalization processing to unify data of different types and ranges into the same format and scale, facilitating subsequent analysis. Subsequently, in the control module 3, the control module 3 selects or calls a Long Short-Term Memory (LSTM) network to construct an energy consumption prediction model. This model uses the filtered and normalized data as input and the energy consumption prediction data of the truck crane as output to predict the energy consumption of the truck crane.

[0042] Specifically, Long Short-Term Memory (LSTM) networks have a unique memory unit structure that can effectively process time-series data and uncover long-term dependencies within the data. By performing deep training on a large amount of historical operating data and corresponding energy consumption data, it can accurately identify potential correlation patterns between different operating conditions such as unloaded driving, light-load operation, and heavy-load lifting, and energy consumption.

[0043] For example, when the energy consumption prediction model determines that the current operating condition is no-load driving, the control module 3 sends a command to the engine control system to reduce the engine speed from the normal range to the economic operating range by adjusting the engine's fuel injection method and ignition timing. Simultaneously, the power output of the electric hydraulic pump is reduced to minimize unnecessary energy consumption. Under light-load operating conditions, the engine speed and electric hydraulic pump power are adjusted (increased or decreased) appropriately according to the specific load conditions to ensure efficient energy utilization while meeting operational requirements. Under heavy-load lifting conditions, when a larger power output is predicted, the control module 3 promptly increases the engine speed to increase power output, and simultaneously uses a PID control algorithm to precisely adjust the servo motor speed of the electric hydraulic pump.

[0044] Therefore, under heavy load, the control module 3 adjusts the servo motor speed (electrical adjustment) through the PID algorithm to stabilize the hydraulic system pressure at the set value ±0.5MPa (hydraulic effect), ensuring smooth operation of the crane boom.

[0045] In practical applications, for example, under no-load conditions, the target engine speed is set to 1200 rpm, and the displacement of the electric hydraulic pump is reduced to 30% of the rated value; under heavy-load conditions, the engine speed is increased to 2200 rpm, and the servo motor speed is adjusted by setting Kp=0.8, Ki=0.2, and Kd=0.1 in the PID algorithm, so that the hydraulic system pressure is stabilized within the set value ±0.5MPa range.

[0046] Specifically, in some optional implementations of this embodiment, the PID control algorithm, through the coordinated action of proportional, integral, and derivative components, can quickly and accurately adjust the speed of the servo motor based on the deviation between the actual value and the set value of the hydraulic system pressure, thereby precisely controlling the output flow and pressure of the electric hydraulic pump and ensuring that the hydraulic system has sufficient power to drive the crane boom to move smoothly and efficiently.

[0047] Furthermore, in the prior art, when the high-voltage power battery is working, it converts high-voltage electricity into low-voltage electricity through a DC-DC converter to continuously power the low-voltage battery 4 and the low-voltage system. However, this power supply method causes certain energy loss and waste, reducing energy utilization efficiency. In order to further increase the energy-saving effect of the truck crane chassis, a low-voltage battery 4 is also provided in this embodiment of the invention, so that the low-voltage battery 4 supplies power to the low-voltage control system (the low-voltage control system refers to a system composed of electrical components controlled by 24V electricity, which is the power supply system of the whole vehicle).

[0048] Specifically, such as Figure 2 As shown in this embodiment of the invention, to effectively reduce energy loss, the power supply management of the low-voltage battery 4 is optimized, including setting a high voltage threshold and a low voltage threshold. When the voltage of the low-voltage battery 4 is higher than the high threshold, it indicates that the battery has sufficient charge. At this time, the vehicle control unit (VCU) detects this state and promptly controls the output of the DC-DC converter to cut off the charging of the low-voltage battery 4 by the high-voltage power battery. During this stage, the low-voltage system relies entirely on the low-voltage battery 4 for power, avoiding unnecessary energy conversion losses. As the low-voltage system continues to operate, the charge of the low-voltage battery 4 gradually decreases. When the voltage falls below the set low threshold, it indicates that the battery is low on charge. After detecting this situation, the VCU opens the output of the DC-DC converter. At this time, the high-voltage power battery not only charges the low-voltage battery 4 but also directly supplies power to the low-voltage system, ensuring the stable operation of the low-voltage control system and meeting the equipment's operating requirements.

[0049] In some optional implementations of this embodiment, for example, the highest voltage threshold is set to 23.8V, corresponding to 80% battery capacity; and the lowest voltage threshold is set to 22.6V, corresponding to 20% battery capacity.

[0050] For example, the VCU collects the voltage of the low-voltage battery 4 in real time through the ADC module: when the voltage is ≥23.8V, it outputs a PWM signal to turn off the DC-DC converter (efficiency ≥95%), and the low-voltage system consists of two 12V / 180Ah lead-acid batteries connected in series; when the voltage is ≤22.6V, it turns on the DC-DC converter, and the high-voltage battery (400V) charges the low-voltage battery 4 and supplies power to the system through the converter. The charging current is limited to 20A to avoid overcharging.

[0051] This configuration, through dynamic adjustment of the electrical system (such as motor power), cuts off the DC-DC converter when the low-voltage battery 4 voltage is higher than the high threshold and turns on the DC-DC converter when it is lower than the low threshold, thereby achieving precise drive of the hydraulic system and avoiding the energy loss caused by the independent operation of the traditional hydraulic system. The hydraulic power transmission efficiency is improved by 12%. Compared with the fixed power of the hydraulic pump in the prior art, the embodiment of the present invention makes the hydraulic output precisely match the working condition requirements through the above-mentioned electrical parameter adjustment, thereby reducing energy loss and energy waste from the source.

[0052] Therefore, in this embodiment of the invention, the above-mentioned threshold-based power supply method enables intelligent regulation of the power supply to the low-voltage battery 4, effectively improving the energy utilization efficiency of the crane.

[0053] Specifically, in this embodiment of the invention, dynamically adjusting the hydraulic system of the truck crane chassis based on the predicted results includes:

[0054] After the energy consumption prediction model determines the current operating conditions, the control module will quickly send instructions to the engine control system. By adjusting the engine's fuel injection strategy and ignition timing, the engine speed will be adjusted. The PID control algorithm will be used to precisely adjust the speed of the servo motor of the electric hydraulic pump, thereby precisely controlling the output flow and pressure of the electric hydraulic pump and ensuring that the hydraulic system has sufficient power to drive the crane boom to move smoothly and efficiently.

[0055] Therefore, the energy-saving control system for a truck crane chassis provided by this invention dynamically adjusts the electrical and hydraulic systems of the truck crane chassis, effectively suppresses interference in sensor signals through filtering by the data processing module, and eliminates the differences in data scales of different sensors through normalization processing, thereby reducing the error of the input data of the energy consumption prediction model by more than 30%, and solving the problem of "high energy consumption due to independent operation" in the prior art.

[0056] Secondly, such as Figure 3 As shown, this embodiment of the invention also provides an energy-saving control method for a truck crane chassis, the method comprising the following steps S100-S400:

[0057] Step S100: Detect the torque change data and pressure data of various parts of the truck crane's hydraulic system during the power transmission process;

[0058] In some optional implementations of this embodiment, the detection data is detected by a torque detection device and a pressure detection device. During the data detection process, the torque detection device is installed at the connection between the engine and the transmission system of the truck crane; the number of pressure detection devices includes multiple devices, which are installed at the hydraulic pipeline nodes of the truck crane.

[0059] Preferably, the torque detection device includes a torque sensor.

[0060] For example, a high-precision torque sensor with high measurement accuracy and fast sampling frequency is installed at the connection between the engine and the transmission system, thus enabling real-time and accurate monitoring of torque changes during power transmission. Pressure sensors are distributed at key nodes of the hydraulic pipeline. Preferably, the pressure sensors have good environmental adaptability. In order to make the detected pressure more accurate and adapt to different working temperatures, the temperature operating range of the pressure sensors is preferably -40°C to 120°C. This ensures the accuracy of the pressure data collected from various parts of the hydraulic system and provides an important basis for the system to understand the working status of the hydraulic system.

[0061] Step S200: Preprocess the received torque change data and pressure data;

[0062] Specifically, in this embodiment of the invention, the preprocessing includes filtering and normalization.

[0063] For example, advanced filtering algorithms, such as the Kalman filter, can effectively suppress noise and retain real and valid signals based on the dynamic characteristics of the data. Through normalization processing, data of different types and ranges are unified to the same format and scale, and the data generated after the signal normalization processing is used as data for training energy consumption prediction models.

[0064] Step S300: Using the preprocessed data after training as input data, construct an energy consumption prediction model using a long short-term memory network;

[0065] During the training process, the Long Short-Term Memory (LSTM) network is iteratively trained using historical operating data of the vehicle. The backpropagation algorithm is used to continuously adjust the weight parameters of the LSM network, enabling the energy consumption prediction model to accurately learn the energy consumption variation patterns under different operating conditions. The energy consumption prediction data of the truck crane is used as the output.

[0066] In some optional implementations of this embodiment, historical operating condition data includes: vehicle speed, engine speed, hydraulic line pressure, load weight, and energy consumption data.

[0067] Step S400: Predict the energy consumption of the truck crane using the constructed energy consumption prediction model, and dynamically adjust the electrical and hydraulic systems of the truck crane chassis based on the prediction results.

[0068] For example, based on the operating condition judgment results (no load / light load / heavy load) output by the energy consumption prediction model, differentiated control is implemented on the chassis electrical system:

[0069] Under no-load conditions, a command is sent to the engine control system to adjust the fuel injection strategy to economy mode, reduce the engine speed to 1200rpm±50rpm, and simultaneously reduce the power of the electric hydraulic pump drive motor to 30% of the rated value;

[0070] When lifting heavy loads, first increase the engine speed to 2200 rpm, then use a PID control algorithm (Kp=0.8~1.2, Ki=0.1~0.3, Kd=0.05~0.15) to adjust the speed of the electric hydraulic pump servo motor. Based on the deviation between the actual hydraulic system pressure and the set value, control the hydraulic pump output flow in real time to ensure that the system pressure fluctuation is ≤±0.5MPa when the crane boom moves.

[0071] When operating under light load, the engine speed and hydraulic pump power are dynamically matched based on the load weight data to achieve the optimal balance between energy consumption and operational requirements.

[0072] In practical applications, this invention, through real-time acquisition and processing of torque and hydraulic pressure data, enables the control system to accurately distinguish between no-load, light-load, and heavy-load operating conditions (e.g., low torque sensor data and low hydraulic pressure during no-load conditions; significantly increased torque and pressure during heavy-load conditions), solving the problem of traditional systems' inability to dynamically adjust based on operating conditions. When the predictive model determines a no-load condition, the control module instructs the engine to reduce its speed to the economic range (e.g., from the conventional 2000 rpm to 1200 rpm), avoiding redundant energy consumption at high speeds; during heavy-load conditions, the engine speed is increased in advance to ensure power output, preventing frequent speed reductions due to insufficient power, thus reducing engine energy consumption by 15%-20% compared to traditional systems. After processing the hydraulic system pressure data, the control module can adjust the power output of the electric hydraulic pump in real time (e.g., reducing the displacement to 30% of the rated value during no-load conditions), avoiding energy waste caused by "extensive output" in existing technologies, and improving hydraulic system efficiency by more than 10%.

[0073] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Additionally, the terms "front," "back," "left," "right," "upper," and "lower" in this document refer to the placement shown in the accompanying drawings.

[0074] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An energy-saving control system for a truck crane chassis, characterized in that, include: The sensing module is used to detect torque change data and pressure data of various parts of the hydraulic system of the truck crane during the power transmission process. A data processing module, connected to the sensing module, is used to receive torque change data and pressure data detected by the sensing module, and perform filtering and normalization processing. The control module is connected to the data processing module. The control module can call an energy consumption prediction model that takes filtered and normalized data as input and energy consumption prediction data of the truck crane as output to predict the energy consumption of the truck crane, and dynamically adjust the electrical and hydraulic systems of the truck crane chassis according to the prediction results.

2. The energy-saving control system for a truck crane chassis according to claim 1, characterized in that, The sensing module includes a torque detection device, which is installed at the connection between the engine and the transmission system of the truck crane.

3. The energy-saving control system for a truck crane chassis according to claim 2, characterized in that, The torque detection device includes a torque sensor.

4. The energy-saving control system for a truck crane chassis according to claim 1, characterized in that, The sensing module also includes pressure detection devices, and the number of pressure detection devices includes multiple devices, which are installed at the hydraulic pipeline nodes of the truck crane.

5. The energy-saving control system for a truck crane chassis according to claim 4, characterized in that, The pressure detection device includes a pressure sensor.

6. The energy-saving control system for a truck crane chassis according to claim 1, characterized in that, It also includes a low-voltage battery, which is electrically connected to the control module to provide electrical energy.

7. A method for energy-saving control of a truck crane chassis, characterized in that, include: Detect torque variation data and pressure data of various parts of the hydraulic system of the truck crane during the power transmission process; The received torque and pressure data are preprocessed. Using the preprocessed data after training as input data, an energy consumption prediction model is constructed using a long short-term memory network; The energy consumption of the truck crane is predicted using the constructed energy consumption prediction model, and the electrical and hydraulic systems of the truck crane chassis are dynamically adjusted based on the prediction results.

8. The energy-saving control method for a truck crane chassis according to claim 7, characterized in that, The received torque variation data and pressure data are preprocessed, including filtering and normalization.

9. The energy-saving control method for a truck crane chassis according to claim 7, characterized in that, Using preprocessed data after training as input, an energy consumption prediction model is constructed using a long short-term memory network, including: During the training process, the Long Short-Term Memory (LSTM) network is iteratively trained using historical operating data of the vehicle. The weight parameters of the LSM network are adjusted using the backpropagation algorithm, enabling the energy consumption prediction model to learn the energy consumption variation patterns under different operating conditions. The energy consumption prediction data of the truck crane is used as the output.

10. The energy-saving control method for a truck crane chassis according to claim 9, characterized in that, The historical operating data includes: vehicle speed, engine speed, hydraulic line pressure, load weight, and energy consumption data.

Images