Unmanned container truck hydraulic system oil leakage detection method and system and storage medium

Abstract

The invention relates to an unmanned container truck hydraulic system oil leakage detection method and system and a storage medium, and the method comprises the steps: M1, collecting the data information of the historical liquid level change value of a hydraulic oil tank in the braking process of an unmanned container truck, and obtaining the data information of the flow of a braking oil way in real time based on a flow sensor on the braking oil way; and M2, based on the data information of the flow of the brake oil way, a linear regression prediction algorithm oriented to global search is adopted to predict the liquid level change value of the hydraulic oil tank, and the predicted data information of the liquid level change value of the hydraulic oil tank is obtained. The liquid level change of the hydraulic oil tank can be monitored in real time, the oil leakage event can be quickly responded, and the device is suitable for various complex working conditions and has high environment adaptability.

Description

Technical Field

[0001] This invention relates to the field of unmanned truck technology, and in particular to a method, system and storage medium for detecting oil leakage in the hydraulic system of an unmanned truck. Background Technology

[0002] Unmanned container trucks are used for container transport operations within ports, and their steering and positioning are all completed by a hydraulic system. Hydraulic systems are susceptible to oil leaks, which maintenance personnel cannot detect in a timely manner during operation.

[0003] Oil leakage is a common and potentially hazardous problem in the hydraulic control system of automatic transmissions. It can stem from various factors, including aging seals, worn oil seals, loose or damaged pipes, etc. Traditional methods for detecting oil leaks in hydraulic systems rely heavily on manual inspection, which is inefficient and susceptible to subjective biases. In recent years, with the development of artificial intelligence and big data technologies, data-driven predictive models have gradually become a research hotspot. For example, various techniques for detecting mechanical properties or conditions have been detailed, including hardness testing, folding detection, and contamination detection, which provide theoretical support for oil leak detection in hydraulic systems. However, existing methods still have shortcomings in global search capabilities and optimization accuracy, necessitating a more efficient solution. Summary of the Invention

[0004] In view of the above problems, the present invention provides a method, system and storage medium for detecting oil leakage in the hydraulic system of unmanned trucks. It can not only monitor the changes in hydraulic oil level in the hydraulic tank in real time and respond quickly to oil leakage events, but also is applicable to a variety of complex working conditions and has strong environmental adaptability.

[0005] To achieve the above and other related objectives, the present invention provides the following technical solution: A method for detecting oil leakage in the hydraulic system of an unmanned container truck, the method comprising: During the braking process of the M1 unmanned truck, the historical hydraulic oil level change data of the hydraulic oil tank is collected, and the flow data of the brake oil circuit is obtained in real time based on the flow sensor on the brake oil circuit. M2. Based on the flow rate data of the brake oil circuit, a linear regression prediction algorithm oriented towards global search is used to predict the hydraulic oil tank level change value, and the predicted hydraulic oil tank level change value data is obtained. M3. Based on the data information of the predicted hydraulic oil tank level change value and the data information of the historical hydraulic oil tank level change value, the improved symbiotic biological search algorithm is used to optimize the predicted hydraulic oil tank level change value to obtain the optimized hydraulic oil tank level change value data information. M4. Based on the data information of the optimized hydraulic oil tank level change value, a preset threshold is set. If the optimized hydraulic oil tank level change value is less than the preset threshold, the oil tank is normal. If the optimized hydraulic oil tank level change value is greater than the preset threshold, the oil tank is leaking oil and needs to be inspected or maintained.

[0006] Furthermore, in step M3, the optimization of the predicted hydraulic tank level change value using the improved symbiotic organism search algorithm includes: M31. Based on the predicted hydraulic oil tank level change data and the historical hydraulic oil tank level change data, the parameters of the symbiotic population are initialized to obtain the initialized symbiotic population data. M32. Based on the data information of the initialized symbiotic population, construct the fitness value function SH for individual population members. , Where, x i The parameter values ​​of the i-th individual in the initialized symbiotic population are given by ω, ρ, and β, which are weighting coefficients. The fitness values ​​of the individuals in the population are calculated to obtain the fitness data of the individuals in the population. M33. Based on the fitness values ​​of the individuals in the population, the optimal position is updated, and the entire population sequentially undergoes mutualistic phase updates, symbiotic phase updates, and parasitic operations to obtain the updated population data. M34. Based on the updated population data, construct the objective function JB. , Where θ, α, and δ are any constant parameters between 0 and 1, the target value of population optimization is calculated, and the data information of the target value of population optimization is obtained.

[0007] Furthermore, the optimization of the predicted hydraulic tank level change value using the improved symbiotic organism search algorithm also includes: M35. Based on the data information of the target value of the population optimization, a preset condition threshold is set. If the target value of the population optimization is greater than the condition threshold, steps M32-M33 are repeated. If the target value of the population optimization is less than the condition threshold, the optimal value is output.

[0008] Furthermore, the constraints on the weighting coefficients ω, ρ, and β are as follows: .

[0009] Furthermore, the sum of the squares of the constant parameters θ, a, and δ is 1, and the absolute value of the difference between the constant parameters θ, a, and δ is not equal to zero.

[0010] Furthermore, in step M2, the prediction of the hydraulic tank level change using a global search-oriented linear regression prediction algorithm includes: M21. Based on the flow rate data of the brake fluid circuit, the amount of brake fluid in the brake fluid circuit in different time periods is estimated to obtain the data information of the amount of brake fluid in the brake fluid circuit in different time periods. M22. Input the data information of the brake oil volume in the different time periods into the linear regression prediction model for global search for training and learning, and obtain the trained linear regression prediction model for global search. M23. Based on the trained linear regression prediction model for global search, input the data information of the oil volume in the brake oil circuit during different time periods, predict the change value of the hydraulic oil tank level, and obtain the data information of the predicted change value of the hydraulic oil tank level.

[0011] Furthermore, the linear regression prediction model for global search includes an input layer, a cubic spline function layer, and an output layer, wherein the input layer is connected to the cubic spline function layer, and the cubic spline function layer is connected to the output layer.

[0012] Furthermore, the data information on the amount of brake fluid in the brake fluid circuit during different time periods is the data information on the amount of brake fluid in the brake fluid circuit during different time periods after standardization or normalization processing.

[0013] To achieve the above and other related objectives, the present invention also provides an oil leakage detection system for an unmanned truck hydraulic system, including a computer device programmed or configured to perform the steps of the described oil leakage detection method for an unmanned truck hydraulic system.

[0014] To achieve the above and other related objectives, the present invention also provides a computer-readable storage medium storing a computer program programmed or configured to perform the described method for detecting oil leaks in the hydraulic system of an unmanned truck.

[0015] The present invention has the following positive effects: This invention uses a linear regression prediction algorithm oriented towards global search to predict the hydraulic oil tank level change value, and combines it with an improved symbiotic biological search algorithm to optimize the predicted hydraulic oil tank level change value. This not only significantly reduces the prediction error and improves the detection accuracy through the improved optimization algorithm, but also enables real-time monitoring of hydraulic oil tank level changes, rapid response to oil leakage events, and applicability to various complex working conditions, with strong environmental adaptability. Attached Figure Description

[0016] Figure 1This is a schematic diagram of the method flow of the present invention; Figure 2 This is a flowchart illustrating the linear regression prediction algorithm for global search according to the present invention. Figure 3 This is a flowchart illustrating the improved symbiotic organism search algorithm of the present invention; Figure 4 This is a schematic diagram of the hydraulic system of the present invention.

[0017] The labels in the diagram are as follows: 1-Brake cylinder, 2-Flow sensor, 3-Brake control valve, 4-Level sensor, 5-Hydraulic tank, 6-Level, 61-Stop level. Detailed Implementation

[0018] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0019] Example 1: As Figure 1 As shown, a method for detecting oil leakage in the hydraulic system of an unmanned truck includes: During the braking process of the M1 unmanned truck, the historical hydraulic oil level change data of the hydraulic oil tank is collected, and the flow data of the brake oil circuit is obtained in real time based on the flow sensor on the brake oil circuit. M2. Based on the flow rate data of the brake oil circuit, a linear regression prediction algorithm oriented towards global search is used to predict the hydraulic oil tank level change value, and the predicted hydraulic oil tank level change value data is obtained. M3. Based on the data information of the predicted hydraulic oil tank level change value and the data information of the historical hydraulic oil tank level change value, the improved symbiotic biological search algorithm is used to optimize the predicted hydraulic oil tank level change value to obtain the optimized hydraulic oil tank level change value data information. M4. Based on the data information of the optimized hydraulic oil tank level change value, a preset threshold is set. If the optimized hydraulic oil tank level change value is less than the preset threshold, the oil tank is normal. If the optimized hydraulic oil tank level change value is greater than the preset threshold, the oil tank is leaking oil and needs to be inspected or maintained.

[0020] In this embodiment, as Figure 3 As shown, in step M3, the optimization of the predicted hydraulic tank level change value using the improved symbiotic organism search algorithm includes: M31. Based on the predicted hydraulic oil tank level change data and the historical hydraulic oil tank level change data, the parameters of the symbiotic population are initialized to obtain the initialized symbiotic population data. M32. Based on the data information of the initialized symbiotic population, construct the fitness value function SH for individual population members. , Where, x i The parameter values ​​of the i-th individual in the initialized symbiotic population are given by ω, ρ, and β, which are weighting coefficients. The fitness values ​​of the individuals in the population are calculated to obtain the fitness data of the individuals in the population. M33. Based on the fitness values ​​of the individuals in the population, the optimal position is updated, and the entire population sequentially undergoes mutualistic phase updates, symbiotic phase updates, and parasitic operations to obtain the updated population data. M34. Based on the updated population data, construct the objective function JB. , Where θ, α, and δ are any constant parameters between 0 and 1, the target value of population optimization is calculated, and the data information of the target value of population optimization is obtained.

[0021] In this embodiment, the optimization of the predicted hydraulic tank level change value using the improved symbiotic organism search algorithm further includes: M35. Based on the data information of the target value of the population optimization, a preset condition threshold is set. If the target value of the population optimization is greater than the condition threshold, steps M32-M33 are repeated. If the target value of the population optimization is less than the condition threshold, the optimal value is output.

[0022] In this embodiment, the constraints on the weighting coefficients ω, ρ, and β are as follows: .

[0023] In this embodiment, the sum of the squares of the constant parameters θ, a and δ is 1, and the absolute value of the difference between the constant parameters θ, a and δ is not equal to zero.

[0024] In this embodiment, taking a certain type of unmanned container truck as an example, assuming the initial hydraulic tank level is 100L, 10 sets of historical hydraulic level changes and corresponding flow rate data were recorded during continuous braking. The future hydraulic level change trend was calculated using a linear regression prediction algorithm, and the predicted value was corrected using an improved symbiotic organism search algorithm. Experimental results show that the error between the optimized hydraulic level change value and the actual measured value was reduced by approximately 15%, significantly improving detection accuracy.

[0025] Example 2: Based on the method for detecting oil leakage in the hydraulic system of an unmanned truck in Example 1, the present invention will be further explained and described below.

[0026] like Figure 1 As shown in Figure 4, a method for detecting oil leakage in the hydraulic system of an unmanned truck includes: During the braking process of the M1 unmanned truck, the historical liquid level change data of the hydraulic oil tank 5 is collected, and the flow data of the brake oil circuit is obtained in real time based on the flow sensor 2 on the brake oil circuit (wherein, the historical liquid level change data is obtained by interpolating the historical liquid level 6 and the shutdown liquid level 61 through the hydraulic sensor 4 on the hydraulic oil tank 5, and the brake control valve 3 is activated, and the oil in the hydraulic oil tank 5 enters the brake cylinder 1). M2. Based on the flow rate data of the brake oil circuit, a linear regression prediction algorithm oriented towards global search is used to predict the hydraulic oil tank level change value, and the predicted hydraulic oil tank level change value data is obtained. M3. Based on the data information of the predicted hydraulic oil tank level change value and the data information of the historical hydraulic oil tank level change value, the improved symbiotic biological search algorithm is used to optimize the predicted hydraulic oil tank level change value to obtain the optimized hydraulic oil tank level change value data information. M4. Based on the data information of the optimized hydraulic oil tank level change value, a preset threshold is set. If the optimized hydraulic oil tank level change value is less than the preset threshold, the oil tank is normal. If the optimized hydraulic oil tank level change value is greater than the preset threshold, the oil tank is leaking oil and needs to be inspected or maintained.

[0027] In this embodiment, as Figure 2As shown, in step M2, the prediction of the hydraulic tank level change using a global search-oriented linear regression prediction algorithm includes: M21. Based on the flow rate data of the brake fluid circuit, the amount of brake fluid in the brake fluid circuit in different time periods is estimated to obtain the data information of the amount of brake fluid in the brake fluid circuit in different time periods. M22. Input the data information of the brake oil volume in the different time periods into the linear regression prediction model for global search for training and learning, and obtain the trained linear regression prediction model for global search. M23. Based on the trained linear regression prediction model for global search, input the data information of the oil volume in the brake oil circuit during different time periods, predict the change value of the hydraulic oil tank level, and obtain the data information of the predicted change value of the hydraulic oil tank level.

[0028] In this embodiment, the linear regression prediction model for global search includes an input layer, a cubic spline function layer, and an output layer. The input layer is connected to the cubic spline function layer, and the cubic spline function layer is connected to the output layer.

[0029] In this embodiment, the data information on the amount of brake fluid in the brake fluid circuit during different time periods is the data information on the amount of brake fluid in the brake fluid circuit during different time periods after standardization or normalization processing.

[0030] In this embodiment, the present invention provides an oil leakage detection system for an unmanned truck hydraulic system, including a computer device that is programmed or configured to perform the steps of the unmanned truck hydraulic system oil leakage detection method.

[0031] In this embodiment, the present invention provides a computer-readable storage medium storing a computer program programmed or configured to perform the described method for detecting oil leaks in the hydraulic system of an unmanned truck.

[0032] Any references to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0033] In summary, this invention not only enables real-time monitoring of hydraulic oil tank level changes and rapid response to oil leakage events, but also applies to various complex working conditions and has strong environmental adaptability.

[0034] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for detecting hydraulic system oil leakage of an unmanned container truck, characterized in that, The method comprises: M1. During the braking process of the unmanned container truck, data information of historical liquid level change values of the hydraulic oil tank is collected, and data information of the flow of the brake oil circuit is obtained in real time based on a flow sensor on the brake oil circuit; M2. Based on the data information of the flow of the brake oil circuit, a linear regression prediction algorithm oriented to global search is used to predict the liquid level change values of the hydraulic oil tank, so as to obtain data information of the predicted liquid level change values of the hydraulic oil tank; M3. Based on the data information of the predicted liquid level change values of the hydraulic oil tank and the data information of the historical liquid level change values of the hydraulic oil tank, an improved symbiotic organism search algorithm is used to optimize the predicted liquid level change values of the hydraulic oil tank, so as to obtain data information of the optimized liquid level change values of the hydraulic oil tank; M4. Based on the data information of the optimized liquid level change values of the hydraulic oil tank, a preset threshold value is set, if the optimized liquid level change values of the hydraulic oil tank are less than the preset threshold value, the oil tank is normal, if the optimized liquid level change values of the hydraulic oil tank are greater than the preset threshold value, the oil tank leaks oil and needs to be repaired or maintained.

2. The method of claim 1, wherein, In step M3, the optimization of the predicted liquid level change values of the hydraulic oil tank by using the improved symbiotic organism search algorithm comprises: M31. Based on the data information of the predicted liquid level change values of the hydraulic oil tank and the data information of the historical liquid level change values of the hydraulic oil tank, the parameters of the symbiotic organism population are initialized, so as to obtain data information of the initialized symbiotic organism population; M32. Based on the data information of the initialized symbiotic organism population, a fitness value function SH of population individuals is constructed, ， wherein x i is the parameter value of the i-th individual of the initialized symbiont population, and ω, ρ and β are weight coefficients, and the fitness value of the population individual is calculated to obtain data information of the fitness value of the population individual. M33. Based on the data information of the fitness value of the population individuals, an optimal position is updated, the whole population is sequentially updated in mutual benefit stage, symbiotic stage and parasitic operation, so as to obtain data information of the updated population; M34. Based on the data information of the updated population, a target function JB is constructed, ， Wherein, θ, α and δ are any constant parameters between 0 and 1, the target value of population optimization is calculated, and data information of the target value of population optimization is obtained.

3. The method of claim 2, wherein, The optimization of the predicted liquid level change values of the hydraulic oil tank by using the improved symbiotic organism search algorithm further comprises: M35. Based on the data information of the target value of population optimization, a preset condition threshold value is set, if the target value of population optimization is greater than the condition threshold value, steps M32-M33 are repeatedly executed, if the target value of population optimization is less than the condition threshold value, an optimal value is output.

4. The method of claim 2, wherein: The constraint conditions of the weight coefficients ω, ρ and β are 。 5. The method of claim 2, wherein: The sum of squares of the constant parameters θ, α and δ is 1, and the absolute value of the difference between the constant parameters θ, α and δ is not equal to zero.

6. The method of claim 1, wherein, In step M2, the prediction of the liquid level change values of the hydraulic oil tank by using the linear regression prediction algorithm oriented to global search comprises: M21. Based on the data information of the flow of the brake oil circuit, the oil quantity of the brake oil circuit in different time periods is calculated, so as to obtain data information of the oil quantity of the brake oil circuit in different time periods; M22. Inputting the data information of the oil amount of the brake oil way in the different time periods into the linear regression prediction model facing global search for training and learning to obtain the trained linear regression prediction model facing global search; M23. Based on the trained linear regression prediction model facing global search, inputting the data information of the oil amount of the brake oil way in the different time periods to predict the liquid level change value of the hydraulic oil tank to obtain the data information of the predicted liquid level change value of the hydraulic oil tank.

7. The method of claim 6, wherein: The linear regression prediction model facing global search comprises an input layer, a cubic spline function layer and an output layer, the input layer is connected with the cubic spline function layer, and the cubic spline function layer is connected with the output layer.

8. The method of claim 6, wherein: The data information of the oil amount of the brake oil way in the different time periods is the data information of the oil amount of the brake oil way in the different time periods after standardization or normalization processing.

9. An unmanned container truck hydraulic system oil leakage detection system, comprising a computer device, characterized in that, The computer device is programmed or configured to execute the steps of the unmanned container truck hydraulic system oil leakage detection method in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program programmed or configured to execute the unmanned container truck hydraulic system oil leakage detection method in any one of claims 1-8.

Images