Engineering mechanical property analysis method and system and excavator

Abstract

The invention discloses an engineering mechanical property analysis method and system and an excavator. The engineering mechanical property analysis cost can be reduced. The engineering mechanical property analysis method comprises the following steps: acquiring signal data of engineering machinery; wherein the signal data comprises engine state data, hydraulic state data and program control signal data; determining an equipment working condition based on the signal data and a working condition identification model; wherein training samples of the working condition recognition model are historical signal data and correspondingly marked working condition types; obtaining working data of a hydraulic system of the engineering machinery based on the equipment working condition and the signal data; and obtaining the hydraulic system performance of the engineering machinery based on the working data of the hydraulic system.

Description

Technical Field

[0001] The present application relates to the technical field of engineering machinery, and in particular to an engineering machinery performance analysis method, system and excavator. Background Art

[0002] As important equipment in the fields of construction, mining and infrastructure construction, the stability and efficiency of the performance of construction machinery are directly related to the quality and progress of engineering projects. However, in actual applications, the performance of construction machinery is often affected by many factors. In different working conditions, the use status and fuel efficiency of construction machinery vary greatly. Its performance analysis is relatively complex, requiring the use of precision instruments, consuming a lot of resources and having high analysis costs. Summary of the invention

[0003] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide a method, system and excavator for analyzing the performance of an engineering machinery, which can reduce the cost of analyzing the performance of the engineering machinery.

[0004] According to the first aspect of the present application, a method for analyzing the performance of engineering machinery is provided, comprising: acquiring signal data of the engineering machinery; wherein the signal data comprises engine status data, hydraulic status data and program-controlled signal data; determining the equipment operating condition based on the signal data and an operating condition identification model; wherein the training samples of the operating condition identification model are historical signal data and corresponding marked operating condition types; obtaining the operating data of the hydraulic system of the engineering machinery based on the equipment operating condition and the signal data; and obtaining the hydraulic system performance of the engineering machinery based on the operating data of the hydraulic system.

[0005] As a possible implementation method, the equipment operating condition is determined based on the signal data and the operating condition identification model, including: determining the total working intensity parameter based on the engine status data; determining the working gear based on the program-controlled signal data; obtaining the pilot control signal based on the hydraulic status data; determining the number of actions, action intensity and working ratio of the engineering machinery based on the pilot control signal; inputting the total working intensity parameter, the working gear, the number of actions, the action intensity and the working ratio into the operating condition identification model to obtain the equipment operating condition.

[0006] As a possible implementation method, the method for constructing the operating condition identification model includes: acquiring historical signal data and typical operating condition data of construction machinery; marking the equipment operating conditions corresponding to the typical operating condition data; using the typical operating condition data as sample data and the equipment operating conditions corresponding to the typical operating condition data as labels to construct a preliminary operating condition identification model; performing operating condition identification on the historical signal data through an integrated learning algorithm to obtain an identification result; and performing model correction and parameter optimization on the preliminary operating condition identification model based on the identification result to obtain a working condition identification model.

[0007] As a possible implementation method, based on the equipment operating condition and the signal data, the working data of the hydraulic system of the engineering machinery is obtained, including: based on the equipment operating condition and the signal data, a plunger pump control curve and a pump efficiency curve are obtained; wherein the signal data include pump current parameters and pump pressure parameters; according to the plunger pump control curve, the real-time pump flow is obtained; according to the pump efficiency curve and the real-time pump flow, the real-time pump efficiency is obtained; according to the real-time pump efficiency and the pump rated torque, the real-time pump torque is obtained; according to the shown real-time pump torque and the time parameters of the preset time period, a pump torque distribution diagram within a preset time period is obtained.

[0008] As a possible implementation method, based on the equipment operating condition and the signal data, the working data of the hydraulic system of the engineering machinery is obtained, which also includes: based on the real-time pump torque, pump pressure parameters and pump current parameters, a pump torque-pump pressure thermal distribution diagram and a pump pressure-pump current thermal distribution diagram are obtained; wherein, based on the working data of the hydraulic system, the hydraulic system performance of the engineering machinery is obtained, including: based on the pump torque-pump pressure thermal distribution diagram, the pump pressure-pump current thermal distribution diagram and preset standards, the real-time working status of the pump is obtained; wherein, the real-time working status of the pump reflects the hydraulic system performance of the engineering machinery.

[0009] As a possible implementation method, based on the equipment operating condition and the signal data, the working data of the hydraulic system of the engineering machinery is obtained, which also includes: acquiring the engine universal curve; obtaining the engine working state heat map based on the pump torque distribution diagram and the engine universal curve; wherein, based on the working data of the hydraulic system, the hydraulic system performance of the engineering machinery is obtained, including: obtaining the engine real-time fuel consumption and the engine real-time efficiency according to the engine working state heat map; obtaining the engine real-time working state based on the engine real-time fuel consumption and the engine real-time efficiency; wherein the engine real-time working state reflects the hydraulic system performance of the engineering machinery; based on the real-time working state of the engine and the real-time working state of the pump, the hydraulic system of the engineering machinery is evaluated to obtain the hydraulic system performance of the engineering machinery.

[0010] As a possible implementation method, based on the signal data and the operating condition identification model, determining the equipment operating condition also includes: based on the signal data, obtaining the proportion of the walking ratio; when the proportion of the shown walking ratio is greater than a preset proportion value, determining that the equipment operating condition is a walking condition; based on the signal data, obtaining the presence of a crushing leader signal; when the crushing leader signal exists, determining that the equipment operating condition is a crushing condition.

[0011] According to the second aspect of the present application, there is provided a construction machinery performance analysis system, comprising: a device side, the device side comprising a multi-source data acquisition platform, a main controller and an edge calculator; the multi-source data acquisition platform is communicatively connected to the main controller, the main controller is communicatively connected to the edge calculator, the multi-source data acquisition platform is used to collect signal data of construction machinery, the main controller is used to execute the construction machinery performance analysis method described in any one of the first aspects above, and the edge calculator is used to deploy the working condition identification model; a remote server side, the remote server side is communicatively connected to the edge calculator, and the remote server side is used to generate an evaluation report based on the hydraulic system performance of the construction machinery.

[0012] As a possible implementation method, the signal data of the construction machinery includes engine status data, hydraulic status data, and program-controlled signal data; wherein, the engine status data includes engine speed, actual torque, fuel injection amount, water temperature, instantaneous fuel consumption and cumulative fuel consumption, and the hydraulic status data includes the oil inlet pressure and oil outlet pressure of the plunger pump, pilot pressure, handle passage status and passage duration, and pedal passage status and passage duration; the program-controlled signal data is used to control the engine's target output speed, gear position, and target torque.

[0013] According to the third aspect of the present application, there is provided an excavator, comprising: a handle, a foot pedal, an engine and a hydraulic system, wherein the handle, the foot pedal, the engine and the hydraulic system output signal data; and an engineering machinery performance analysis system as described in any one of the above second aspects, wherein the engineering machinery performance analysis system is communicatively connected with the handle, the foot pedal, the engine and the hydraulic system.

[0014] The engineering machinery performance analysis method, system and excavator provided in this application can collect signal data using the sensors provided by the engineering machinery, and determine the equipment working conditions in combination with the model. It is suitable for big data scenarios, and does not require the installation of additional sensors to collect the working data of the engineering machinery, which does not increase additional costs, thereby reducing the cost of performance analysis. Determining the working conditions provides a data basis for subsequent performance analysis, which improves the accuracy of performance analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0016] Figure 1 It is a schematic diagram of the operating principle of an engineering machinery performance analysis system provided by an exemplary embodiment of the present application.

[0017] Figure 2 It is a flow chart of a method for analyzing the performance of engineering machinery provided by an exemplary embodiment of the present application.

[0018] Figure 3 It is a structural schematic diagram of an engineering machinery performance analysis device provided by an exemplary embodiment of the present application.

[0019] Figure 4 It is a structural diagram of an electronic device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0020] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0021] Exemplary Systems

[0022] This exemplary embodiment provides a construction machinery performance analysis system including: a device side, the device side includes a multi-source data acquisition platform, a main controller and an edge calculator; the multi-source data acquisition platform is communicatively connected to the main controller, the main controller is communicatively connected to the edge calculator, the multi-source data acquisition platform is used to collect signal data of the construction machinery, the main controller is used to execute the construction machinery performance analysis method provided in the exemplary method below this application, and the edge calculator is used to deploy a working condition identification model; a remote server side, the remote server side is communicatively connected to the edge calculator, and the remote server side is used to generate an evaluation report based on the hydraulic system performance of the construction machinery.

[0023] In view of the multi-source data characteristics of construction machinery, a multi-source data acquisition and computing platform with low latency, low cost and low bit error rate can be established. The multi-source data acquisition platform is used to collect signal data of construction machinery, while the main controller and edge calculator are used to process signal data. The remote server is used to remotely receive data transmitted by the device, and after integrated algorithm processing, the model is established, corrected and generalized, and the model is integrated into the device and the cloud for identifying working conditions. In addition, the remote server can also generate evaluation information about the hydraulic system through data transmission and working condition identification according to a specific calculation process, and compare it with the existing database evaluation information to find differences and room for improvement.

[0024] In some embodiments, the signal data of the engineering machinery may include engine status data, hydraulic status data, program control signal data, etc.

[0025] As a possible implementation method, the engine status data includes engine speed, actual torque, injection amount, water temperature, instantaneous fuel consumption and cumulative fuel consumption; the hydraulic status data includes the inlet pressure and outlet pressure of the plunger pump, pilot pressure, handle passage status and passage duration, and pedal passage status and passage duration; the programmed signal data is used to control the engine's target output speed, gear position and target torque.

[0026] As a possible implementation method, the engine status data is captured by the engine auxiliary sensor, sent from the ECU (Electronic Control Unit) in the form of engine message, and parsed and transcoded to the main controller. The hydraulic status data is measured by the pressure sensor, collected and integrated into the main controller. The control program is integrated in the main controller.

[0027] In some embodiments, the multi-source data acquisition platform can access the CAN bus data, serial port data, Wifi data, etc. of the whole machine of the engineering machinery equipment to collect data. The main controller accumulates and calculates the motion data of the engineering machinery through the signal data collected from various places by the multi-source data acquisition platform, and synchronously collects the hydraulic system information and transmits it to the edge computer. The edge computer transmits the data collected by the device end to the remote server end via the wireless network card on the device end. The remote server end processes the data transmitted by the device end. For example, when the engineering machinery is an excavator, it contains the intensity, frequency and other information of the excavator boom, dipper, bucket, rotation, walking and other actions, and marks the corresponding working conditions. Collect typical working conditions and typical data in typical working conditions during the working process of the engineering machinery, establish a working condition recognition model, and on this basis, modify and generalize the working condition recognition model through big data to realize working condition recognition. The working condition recognition model can be deployed on the edge computer. Therefore, the device end transmits the signal data collected by the engineering machinery through the multi-source data acquisition platform within the preset time to the edge computer after being parsed by the main controller, so as to realize the working condition prediction within the preset time. After obtaining the current working conditions, the edge computer calculates and analyzes the working conditions of the construction machinery through models, and analyzes the key indicators of the hydraulic system. The remote server identifies the working conditions of the construction machinery and generates an evaluation report on the performance of the hydraulic system of the construction machinery in combination with the hydraulic system data feedback of the construction machinery.

[0028] Exemplary excavator

[0029] As a typical engineering machinery, excavators are widely used in various working conditions, such as leveling, trenching, throwing, walking, crushing, etc. However, for excavators of the same tonnage, different working conditions will lead to great differences in the use status and fuel consumption efficiency of the whole machine; the development of similar models with different configurations is also prone to huge differences in the use status and market performance of the whole machine due to differences in some configurations. The existing equipment development and testing methods are limited by environmental factors, and the samples taken are not large. The use of big data is conducive to expanding the sample and reducing the errors and mistakes caused by insufficient sample size. Based on this, in order to improve the accuracy of the analysis of excavator performance, an excavator is provided, including: a handle, a pedal, an engine and a hydraulic system, and the handle, the pedal, the engine and the hydraulic system output signal data; such as the engineering machinery performance analysis system provided above, the engineering machinery performance analysis system is connected to the handle, the pedal, the engine and the hydraulic system in communication.

[0030] Figure 1 This is a schematic diagram of the operating principle of an engineering machinery performance analysis system provided by an exemplary embodiment of the present application. Taking an excavator as an example, refer to Figure 1The overall operation process of the engineering machinery performance analysis system is described in detail: the multi-source data acquisition platform 104 collects the engine state 101, hydraulic state 102 and program control signal 103 from the excavator. After the engine state 101, hydraulic state 102 and program control signal 103 are transmitted to the main controller 105, the main controller 105 parses and transmits the parsed data to the edge calculator 106, and the working condition identification model is arranged at the edge calculator 106. The edge calculator 106 calculates and analyzes the working condition of the excavator through the model (see S201-S205), first collects typical working conditions and sample big data (S201), and then establishes, corrects and generalizes the model through the integrated learning algorithm (S202) (S203), and after completing the model integration (S204), the model is arranged at the edge calculator 106. The edge calculator 106 also identifies the working condition through cloud computing (S205). After obtaining the current working condition, the remote server generates an evaluation report (S206) based on the working condition identification of the excavator and the feedback of the hydraulic system data of the excavator according to the judgment.

[0031] Exemplary Methods

[0032] Existing working condition identification methods mostly use the method of adding sensors, such as adding angle encoders, displacement sensors, flow meters, laser radars, cameras, vibration sensors, etc., which increases the operating cost of engineering machinery and increases the number of areas where failures occur. In order to reduce the cost of determining working conditions in the above performance analysis, a construction machinery performance analysis system based on the above construction is proposed. Figure 2 is a flow chart of a method for analyzing the performance of an engineering machine provided by an exemplary embodiment of the present application, see Figure 1 , the engineering machinery performance analysis method includes: obtaining the signal data of the engineering machinery (see Figure 1 S10 in the figure); wherein the signal data includes engine status data, hydraulic status data and program-controlled signal data. The signal data is derived from various signals generated by the engineering machinery itself and can be collected using sensors provided by the engineering machinery without adding any additional cost. The program-controlled signal data represents program-controlled signal data. Based on the signal data and the working condition identification model, the equipment working condition is determined (see Figure 1 S20 in ), the big data algorithm is used to identify the working condition of the excavator. As the data sample increases, the accuracy can be steadily improved; the training samples of the working condition recognition model are historical signal data and corresponding marked working condition types; based on the equipment working condition and signal data, the working data of the hydraulic system of the construction machinery is obtained (see Figure 1 In S30 in FIG. 1 , when the equipment working condition is known, the hydraulic system of the construction machinery can be further analyzed; based on the working data of the hydraulic system, the hydraulic system performance of the construction machinery can be obtained (see Figure 1S40 in the hydraulic system), based on big data analysis of data collected by the hydraulic system terminal, on the basis of working condition identification, it can realize rapid analysis of hydraulic system control efficiency and fuel consumption, provide support for hydraulic control system performance evaluation, and then improve control strategies and enhance the product competitiveness of construction machinery.

[0033] Combined with the following Figure 1 , a more detailed introduction to the engineering machinery performance analysis method provided in the embodiments of the present application is given.

[0034] In S10, the signal data of the engineering machinery is obtained. The signal data of the engineering machinery is derived from the signal data collected by the sensors of the engineering machinery, such as engine status data, hydraulic status data and program control signal data, etc. The engine status data includes engine speed, actual torque, fuel injection amount, water temperature, instantaneous fuel consumption and cumulative fuel consumption, etc. The hydraulic status data includes the oil inlet pressure and oil outlet pressure of the plunger pump, the pilot pressure, the handle passage state and passage duration, and the pedal passage state and passage duration. The program control signal (program control signal) data is used to control the target output speed and gear position and target torque of the engine. The engine status data is captured by the engine auxiliary sensor, the hydraulic status data is measured by the pressure sensor, and the control program is integrated in the main controller. Therefore, all signal data do not need to be measured by additional measuring instruments (such as angle encoders, displacement sensors, flow meters, laser radars, cameras, vibration sensors, etc.), which reduces the use cost and reduces the impact of the failure of additional measuring instruments on the operation of the engineering machinery, that is, the operation stability and practicality of the engineering machinery are improved.

[0035] In some embodiments, when the engineering machinery is an excavator, the acquisition of signal data can be completed by collecting hydraulic pressure, handle signals and pedal signals using the excavator's own sensors. For example, for the collection of hydraulic flow, there is no need to use a flow meter. The flow meter is a precision instrument with a high cost, and it is unidirectional and easy to damage. The excavator has a harsh working environment. The hydraulic flow is converted by combining the electric control machine pump valve current with the pressure and pump current-pump flow curve, which reduces the cost and improves the practicality. For the judgment of the rise and fall of the boom, there is no need to use a displacement sensor. The displacement sensor is a precision instrument with a high cost, and the working device is easy to be damaged during the operation when the sensor is integrated. The excavator working condition can be judged by a specific algorithm, and the use of the displacement sensor component is eliminated, which not only reduces the cost but also improves the practicality. For the judgment of hydraulic rotation and the rise and fall of the boom, there is no need to use an angle encoder. Most excavators do not have an angle encoder component. A specific algorithm can be used to judge the excavator working condition, and the use of the angle encoder component is eliminated, which reduces the cost and improves the practicality.

[0036] In S20, the equipment working condition is determined based on the signal data and the working condition identification model. The training samples of the working condition identification model are the historical signal data and the corresponding marked working condition types. Through big data modeling and model optimization, multiple algorithms are targeted for modeling and optimization, with low cost and low bit error rate. It is not restricted by the idleness of additional acquisition instruments, and the accuracy can be steadily improved as the data sample increases.

[0037] As a possible implementation method of S20, S20 may include: based on signal data, obtaining the proportion of the walking ratio; when the proportion of the shown walking ratio is greater than a preset proportion value, determining that the equipment operating condition is a walking condition; based on signal data, obtaining the existence of a crushing leader signal; when a crushing leader signal exists, determining that the equipment operating condition is a crushing condition.

[0038] Taking the construction machinery as an excavator as an example, due to the particularity of the walking condition, as long as the walking ratio reaches the preset ratio value, the condition can be determined as the walking condition, which is relatively easy to identify. Due to the particularity of the crushing condition, the presence of the crushing precursor signal can be identified and is easy to identify. Therefore, these two conditions can establish a relatively simple identification process without analyzing other signal data.

[0039] As a possible implementation method of S20, S20 may include: determining the total work intensity parameters based on engine status data; determining the working gear based on the program signal data; obtaining the pilot control signal based on the hydraulic status data; determining the number of actions, action intensity and working ratio of the construction machinery based on the pilot control signal; inputting the total work intensity parameters, working gear, number of actions, action intensity and working ratio into the working condition identification model to obtain the equipment working condition.

[0040] Taking the construction machinery as an example, in addition to the two relatively easy-to-identify working conditions of walking and crushing, excavators also have leveling conditions, trenching conditions and dumping conditions. Among them, for more complex working conditions such as leveling conditions, trenching conditions and dumping conditions, comprehensive judgment can be made through multi-faceted and multi-dimensional signal data. For example, the engine state, the fuel consumption data is obtained through the multi-source data acquisition platform, and the total work intensity is calculated at the main controller. The program control signal obtains the gear data through the multi-source data acquisition platform and is calculated as the gear at the main controller. The hydraulic state, the boom lifting pilot frequency is calculated as the boom lifting times, and the boom lifting intensity is calculated as the boom lifting ratio. The pilot control signal is taken, and the other action times are respectively calculated as: boom lowering times, bucket unloading times, bucket digging times, bucket times, rotation times and walking times, and the above are used as frequency information. The pilot control signal is taken, and the other action intensities are respectively calculated as: boom lowering ratio, bucket unloading ratio, bucket digging ratio, bucket ratio, rotation ratio and walking ratio. The pilot control signal here can be a handle signal and a pedal signal.

[0041] As an example, taking the typical working condition of swinging, the boom lowering ratio, arm unloading ratio, arm digging ratio, bucket ratio, rotation ratio, walking ratio, total work intensity, boom lowering times, arm unloading times, arm digging times, bucket times, rotation times, walking times and gear information are respectively calculated as: 10 / 11 / 14 / 14 / 24 / 24 / 0 / 31 / 10 / 16 / 14 / 13 / 24 / 19 / 0 / 8, and the marked working condition is: swinging. After completing the typical data collection, it can be used as a training sample for the subsequent establishment of the working condition recognition model.

[0042] It is understandable that in other embodiments, in addition to determining the working condition through the pilot control signal, the working device posture or cylinder stroke length can also be identified based on the inclination sensor or displacement sensor of the bucket, dipper arm, and boom of the working device.

[0043] After collecting typical working condition data such as trenching and leveling and marking the corresponding working conditions, the working condition recognition model is trained with this as a training sample, and big data is used to use a variety of machine learning algorithms to identify working conditions, gradually improving the requirements for working condition recognition rate. For example, the method for constructing a working condition recognition model includes: obtaining historical signal data and typical working condition data of construction machinery; marking the equipment working conditions corresponding to the typical working condition data; using the typical working condition data as sample data and the equipment working conditions corresponding to the typical working condition data as labels to construct a preliminary working condition recognition model; using an integrated learning algorithm to identify working conditions on historical signal data to obtain recognition results; based on the recognition results, the preliminary working condition recognition model is corrected and parameters are optimized to obtain a working condition recognition model.

[0044] The various learning algorithms in the ensemble learning algorithm can be: k-nearest neighbor algorithm (compare the sample with the training set data, find the closest k points to determine the working condition), decision tree algorithm (use a tree structure similar to a flowchart to select features for classification and predict working condition results) and support vector machine algorithm (establish a hyperplane that divides the data with the maximum interval to determine the working condition). The results of various machine learning algorithms are combined to identify and output the working condition.

[0045] Taking the decision tree algorithm as an example, when the sample data is large (multiple T sample data), the decision tree binary algorithm is used to classify the working conditions into different working conditions of leveling, digging trenches, and throwing squares. Specifically, in the following binary tree classification, the trunk node where the odd group is located is judged as "yes", and the trunk node where the even group is located is judged as "no":

[0046] By using bucket ratio ≤ 17.5, it is initially divided into: Group 11 and Group 12. Group 11 is mainly composed of samples of flat ground conditions;

[0047] By using the boom lowering ratio ≤7.5, group 11 is divided into group 21 and group 22, where group 21 is a sample of the side-throwing working condition;

[0048] The number of bucket passes is ≤18.5, and group 22 is divided into group 31 and group 32. Group 31 is the sample of flat ground working condition, and group 32 is the sample of trenching working condition;

[0049] By using the rotation ratio ≤ 23.5, group 12 is divided into group 33 and group 34, and group 34 is the square throwing sample;

[0050] By using the rotation ratio ≤ 8.0, group 33 is divided into group 43 and group 44, where group 43 is the flat ground sample;

[0051] By using boom lifting times ≤ 10.5, group 44 is divided into group 51 and group 52. Group 51 is mainly composed of samples of the throwing condition, and group 52 is mainly composed of samples of the trenching condition.

[0052] By using a rotation ratio of ≤18.5, group 51 is divided into group 61 and group 62. Group 61 is a trenching sample, and group 62 is a throwing sample.

[0053] By total work intensity ≤ 14.5, group 52 was divided into: group 63, group 64, group 64 was trenching samples;

[0054] By the number of revolutions ≤ 10.5, group 63 is divided into group 71 and group 72, where group 71 is trenching samples and group 72 is flat ground samples.

[0055] The model is corrected and parameter optimized through the large amount of data collected, and the model is tested and verified. According to the different models of excavators, the key parameters of the model are corrected, and the model is transferred and trained using cloud or local data. The training results are output, and the model deployment is integrated into the controller program, and the controller program is updated to achieve coverage of the client and cloud of the specified electronic control model. After the working condition identification model is deployed to the cloud, it can be pushed in real time through the mobile terminal to realize real-time remote viewing of the equipment working condition.

[0056] It is understandable that the above example does not require the installation of additional sensors. Multiple algorithms are targeted for modeling and optimization, with low cost and low bit error rate. It is not restricted by the idleness of additional acquisition instruments. As the data sample increases, the accuracy can be steadily improved. However, other types of sensors can also be used to collect data, and then the working condition recognition model is constructed through big data to perform working condition recognition. The existing methods for leveling, ditching, and throwing working conditions are mostly linear recognition, and the recognition methods are mostly 1-2 segments, which are relatively simple. With the expansion of data and the advancement of computing power, the use of multiple machine learning algorithms for working condition recognition has a higher feasibility, which not only improves the recognition efficiency, but also improves the recognition accuracy.

[0057] In S30, based on the equipment working condition and signal data, the working data of the hydraulic system of the construction machinery is obtained. Based on the big data analysis of the data collected by the hydraulic system terminal, the performance of the hydraulic system can be further analyzed and evaluated on the basis of working condition identification. Taking the construction machinery as an excavator as an example, the working data of the hydraulic system may include pump current, pump pressure and plunger pump control curve, etc., and the pump efficiency curve can be directly obtained according to the excavator model.

[0058] After obtaining the basic working data of the hydraulic system, further analysis can be performed based on the basic working data. For example, the pump is an important component of the hydraulic system. Specifically, the pump is usually called a hydraulic pump or a driving element (also called a power element) in the hydraulic system. Its main function is to convert the mechanical energy of the prime mover (such as an electric motor, an internal combustion engine, etc.) into the pressure energy of the liquid, thereby providing power for the entire hydraulic system. Based on the equipment working conditions and signal data (pump current and pump pressure, etc.), the plunger pump control curve and the pump efficiency curve are obtained; wherein the signal data includes pump current parameters and pump pressure parameters; according to the plunger pump control curve, the real-time pump flow is obtained; according to the pump efficiency curve and the real-time pump flow, the real-time pump efficiency is obtained; according to the real-time pump efficiency and the pump rated torque, the real-time pump torque is obtained; according to the real-time pump torque shown and the time parameters of the preset time period, the pump torque distribution diagram within the preset time period is obtained. The pump torque distribution diagram can be used to evaluate the use characteristics of the plunger pump and serve as a reference for the evaluation of the use performance of the plunger pump under the working conditions of the excavator.

[0059] After obtaining the pump torque, pump pressure and pump current parameters, the pump torque-pump pressure thermal distribution diagram and the pump pressure-pump current thermal distribution diagram can also be drawn. For example, based on the real-time pump torque, pump pressure parameters and pump current parameters, the pump torque-pump pressure thermal distribution diagram and the pump pressure-pump current thermal distribution diagram are obtained; based on the pump torque-pump pressure thermal distribution diagram, the pump pressure-pump current thermal distribution diagram and the preset standard, the real-time working status of the pump is obtained; wherein, the real-time working status of the pump reflects the performance of the hydraulic system of the construction machinery. The thermal diagram helps to reflect the real-time working status of the pump. Through horizontal comparison across models, configurations, etc., and across machines, the status problems of the pump can be quickly discovered. By improving the concentrated state of the pump torque, the use efficiency of the pump can be improved. Since the pump is an important part of the hydraulic system, the performance of the hydraulic system can also be improved.

[0060] According to the pump torque distribution diagram and thermal distribution diagram obtained above, combined with the engine universal curve, through data fitting, the engine working state thermal diagram can be drawn, such as obtaining the engine universal curve; based on the pump torque distribution diagram and the engine universal curve, the engine working state thermal diagram is obtained; according to the engine working state thermal diagram, the engine real-time fuel consumption and engine real-time efficiency are obtained; based on the engine real-time fuel consumption and engine real-time efficiency, the engine real-time working state is obtained; wherein, the real-time working state of the engine reflects the hydraulic system performance of the engineering machinery; based on the real-time working state of the engine and the real-time working state of the pump, the hydraulic system of the engineering machinery is evaluated to obtain the hydraulic system performance of the engineering machinery. Understanding the real-time fuel consumption and efficiency of the engine can point out the improvement direction for the engine pump valve efficiency matching, realize the real-time evaluation of the system performance of the engineering machinery, and after obtaining the real-time evaluation, the performance of the engineering machinery can be improved according to the real-time evaluation to improve the practicality of the engineering machinery.

[0061] In S40, the hydraulic system performance of the construction machinery is obtained based on the working data of the hydraulic system. Based on the above pump torque distribution diagram, thermal distribution diagram and real-time working state of the engine, the hydraulic system performance of the construction machinery can be comprehensively obtained. The hydraulic system performance is evaluated, and the construction machinery can be improved according to the evaluation results to obtain a construction machinery with better performance or lower cost.

[0062] Exemplary Devices

[0063] Figure 3 is a schematic diagram of the structure of an engineering machinery performance analysis device provided by an exemplary embodiment of the present application, such as Figure 3 As shown, the engineering machinery performance analysis device 5 includes: an acquisition module 51, used to acquire signal data of the engineering machinery; wherein the signal data includes engine status data, hydraulic status data and program-controlled signal data; a determination module 52, used to determine the equipment working condition based on the signal data and the working condition recognition model; wherein the training samples of the working condition recognition model are historical signal data and corresponding marked working condition types; a first calculation module 53, based on the equipment working condition and the signal data, obtains the working data of the hydraulic system of the engineering machinery; a second calculation module 54, based on the working data of the hydraulic system, obtains the hydraulic system performance of the engineering machinery.

[0064] As a possible implementation method, the determination module 52 can be configured as follows: based on the engine status data, determine the total work intensity parameters; based on the program signal data, determine the working gear; based on the hydraulic status data, obtain the pilot control signal; based on the pilot control signal, determine the number of actions, action intensity and working ratio of the construction machinery; input the total work intensity parameters, working gear, number of actions, action intensity and working ratio into the working condition identification model to obtain the equipment working condition.

[0065] As a possible implementation method, the method for constructing the working condition identification model in the engineering machinery performance analysis device 5 can be configured as follows: obtaining historical signal data and typical working condition data of the engineering machinery; marking the equipment working conditions corresponding to the typical working condition data; using the typical working condition data as sample data and the equipment working conditions corresponding to the typical working condition data as labels to construct a preliminary working condition identification model; performing working condition identification on the historical signal data through an integrated learning algorithm to obtain an identification result; and performing model correction and parameter optimization on the preliminary working condition identification model based on the identification result to obtain a working condition identification model.

[0066] As a possible implementation method, the first calculation module 53 can be configured as: based on the equipment operating conditions and signal data, obtain the plunger pump control curve and the pump efficiency curve; wherein the signal data includes pump current parameters and pump pressure parameters; according to the plunger pump control curve, obtain the real-time pump flow; according to the pump efficiency curve and the real-time pump flow, obtain the real-time pump efficiency; according to the real-time pump efficiency and the pump rated torque, obtain the real-time pump torque; according to the shown real-time pump torque and the time parameters of the preset time period, obtain the pump torque distribution diagram within the preset time period.

[0067] As a possible implementation method, the first calculation module 53 can be configured to obtain a pump torque-pump pressure thermal distribution diagram and a pump pressure-pump current thermal distribution diagram based on real-time pump torque, pump pressure parameters and pump current parameters; wherein, the second calculation module 54 can be correspondingly configured to obtain a real-time working status of the pump based on the pump torque-pump pressure thermal distribution diagram, the pump pressure-pump current thermal distribution diagram and preset standards; wherein, the real-time working status of the pump reflects the hydraulic system performance of the construction machinery.

[0068] As a possible implementation method, the first calculation module 53 can be configured to: obtain the engine universal curve; obtain the engine working state heat map based on the pump torque distribution diagram and the engine universal curve; wherein, the second calculation module 54 can be correspondingly configured to: obtain the engine real-time fuel consumption and the engine real-time efficiency according to the engine working state heat map; obtain the engine real-time working state based on the engine real-time fuel consumption and the engine real-time efficiency; wherein, the real-time working state of the engine reflects the hydraulic system performance of the construction machinery; based on the real-time working state of the engine and the real-time working state of the pump, the hydraulic system of the construction machinery is evaluated to obtain the hydraulic system performance of the construction machinery.

[0069] As a possible implementation method, the determination module 52 can also be configured as: based on the signal data, obtaining the proportion of the walking ratio; when the proportion of the shown walking ratio is greater than the preset proportion value, determining that the equipment operating condition is a walking condition; based on the signal data, obtaining the presence of a crushing leader signal; when a crushing leader signal exists, determining that the equipment operating condition is a crushing condition.

[0070] Exemplary Electronic Devices

[0071] An electronic device includes: a processor; a memory for storing instructions executable by the processor; and the processor is used to execute the engineering machinery performance analysis method described in the embodiment provided in the present application.

[0072] Below, reference Figure 4 The electronic device according to the embodiment of the present application is described. The electronic device may be any one or both of the first device and the second device, or a stand-alone device independent of them, and the stand-alone device may communicate with the first device and the second device to receive the collected input signal from them.

[0073] Figure 4 A block diagram of an electronic device according to an embodiment of the present application is illustrated.

[0074] like Figure 4 As shown, the electronic device 60 includes one or more processors 61 and a memory 62 .

[0075] The processor 61 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 60 to perform desired functions.

[0076] The memory 62 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 61 may run the program instructions to implement the engineering machinery performance analysis method of each embodiment of the present application described above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0077] In one example, the electronic device 60 may further include: an input device 63 and an output device 64, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0078] When the electronic device is a stand-alone device, the input device 63 may be a communication network connector for receiving collected input signals from the first device and the second device.

[0079] In addition, the input device 63 may also include, for example, a keyboard, a mouse, etc.

[0080] The output device 64 can output various information to the outside, including the determined distance information, direction information, etc. The output device 64 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0081] Of course, to simplify, Figure 4 Only some of the components related to the present application in the electronic device 60 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 60 may also include any other appropriate components.

[0082] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0083] A computer-readable storage medium stores a computer program, and the computer program is used to execute the engineering machinery performance analysis method described in the embodiment provided in the present application.

[0084] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0085] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for analyzing the performance of engineering machinery, characterized in that: include: Acquiring signal data of the engineering machinery; wherein the signal data includes engine status data, hydraulic status data and program control signal data; Determine the equipment operating condition based on the signal data and the operating condition identification model; wherein the training samples of the operating condition identification model are historical signal data and corresponding marked operating condition types; Based on the equipment operating condition and the signal data, obtaining operating data of the hydraulic system of the engineering machinery; Based on the working data of the hydraulic system, the hydraulic system performance of the construction machinery is obtained.

2. The engineering machinery performance analysis method according to claim 1, characterized in that: Determining the equipment operating condition based on the signal data and the operating condition identification model includes: Determining a total work intensity parameter based on the engine status data; Determining the working gear based on the program-controlled signal data; Based on the hydraulic state data, obtaining a pilot control signal; Based on the pilot control signal, determining the number of actions, action intensity and working ratio of the engineering machinery; The total work intensity parameter, the work gear, the number of actions, the action intensity and the work ratio are input into the working condition identification model to obtain the equipment working condition.

3. The engineering machinery performance analysis method according to claim 1, characterized in that: The method for constructing the operating condition identification model includes: Obtain historical signal data and typical operating condition data of construction machinery; Mark the equipment operating conditions corresponding to the typical operating condition data; Using the typical working condition data as sample data and the equipment working condition corresponding to the typical working condition data as a label, a preliminary working condition recognition model is constructed; Performing working condition identification on the historical signal data by using an integrated learning algorithm to obtain an identification result; Based on the identification result, the preliminary operating condition identification model is corrected and parameters are optimized to obtain an operating condition identification model.

4. The engineering machinery performance analysis method according to claim 1, characterized in that: Based on the equipment working condition and the signal data, obtaining working data of the hydraulic system of the engineering machinery includes: Based on the equipment operating conditions and the signal data, a plunger pump control curve and a pump efficiency curve are obtained; wherein the signal data includes a pump current parameter and a pump pressure parameter; According to the plunger pump control curve, obtaining the real-time pump flow rate; Obtaining real-time pump efficiency according to the pump efficiency curve and the real-time pump flow rate; Obtaining real-time pump torque according to the real-time pump efficiency and the pump rated torque; According to the real-time pump torque shown and the time parameter of the preset time period, a pump torque distribution diagram within the preset time period is obtained.

5. The engineering machinery performance analysis method according to claim 4, characterized in that: Based on the equipment working condition and the signal data, obtaining working data of the hydraulic system of the engineering machinery also includes: Based on the real-time pump torque, pump pressure parameter and pump current parameter, a pump torque-pump pressure thermodynamic distribution diagram and a pump pressure-pump current thermodynamic distribution diagram are obtained; Wherein, based on the working data of the hydraulic system, the hydraulic system performance of the construction machinery is obtained, including: Based on the pump torque-pump pressure thermodynamic distribution diagram, the pump pressure-pump current thermodynamic distribution diagram and preset standards, the real-time working state of the pump is obtained; wherein the real-time working state of the pump reflects the hydraulic system performance of the engineering machinery.

6. The engineering machinery performance analysis method according to claim 5, characterized in that: Based on the equipment working condition and the signal data, obtaining working data of the hydraulic system of the engineering machinery also includes: Get the engine universal curve; Based on the pump torque distribution diagram and the engine universal curve, a thermal diagram of the engine working state is obtained; Wherein, based on the working data of the hydraulic system, the hydraulic system performance of the construction machinery is obtained, including: According to the engine working state thermal diagram, the real-time fuel consumption and the real-time efficiency of the engine are obtained; Based on the real-time fuel consumption of the engine and the real-time efficiency of the engine, the real-time working state of the engine is obtained; wherein the real-time working state of the engine reflects the performance of the hydraulic system of the engineering machinery; Based on the real-time working status of the engine and the real-time working status of the pump, the hydraulic system of the engineering machinery is evaluated to obtain the performance of the hydraulic system of the engineering machinery.

7. The engineering machinery performance analysis method according to claim 1, characterized in that: Based on the signal data and the operating condition identification model, determining the equipment operating condition further includes: Based on the signal data, obtaining a proportion of walking ratio; When the proportion of the walking ratio shown is greater than the preset proportion value, the equipment working condition is determined to be the walking working condition; Based on the signal data, obtaining the existence of a crushing leader signal; When the crushing pilot signal exists, it is determined that the equipment operating condition is a crushing operating condition.

8. A system for analyzing the performance of engineering machinery, characterized in that: include: The device side includes a multi-source data acquisition platform, a main controller and an edge calculator; The multi-source data acquisition platform is communicatively connected to the main controller, the main controller is communicatively connected to the edge computer, the multi-source data acquisition platform is used to collect signal data of engineering machinery, the main controller is used to execute the engineering machinery performance analysis method described in any one of claims 1 to 7, and the edge computer is used to deploy the working condition identification model; A remote server end, the remote server end is communicatively connected to the edge computer, and the remote server end is used to generate an evaluation report based on the hydraulic system performance of the engineering machinery.

9. The engineering machinery performance analysis system according to claim 8, characterized in that: The signal data of the construction machinery include engine status data, hydraulic status data, and program-controlled signal data; wherein, the engine status data include engine speed, actual torque, fuel injection amount, water temperature, instantaneous fuel consumption and cumulative fuel consumption; the hydraulic status data include the oil inlet pressure and oil outlet pressure of the plunger pump, pilot pressure, handle passage status and passage duration, and pedal passage status and passage duration; the program-controlled signal data is used to control the engine's target output speed, gear position, and target torque.

10. An excavator, characterized in that: include: A handle, a foot pedal, an engine and a hydraulic system, wherein the handle, the foot pedal, the engine and the hydraulic system output signal data; The engineering machinery performance analysis system as described in any one of claims 8 to 9 above, wherein the engineering machinery performance analysis system is communicatively connected with the handle, the foot pedal, the engine and the hydraulic system.

Images