Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present invention, are given by way of illustration and explanation only, not limitation.
A general heat dissipation fan of a crane hydraulic system is a constant-speed fan, and heat dissipation control of the hydraulic system is achieved through opening and closing control of the fan. The traditional mode is as follows: when the temperature of the hydraulic oil is less than a certain fixed value W 1 When the fan is closed, the temperature of the hydraulic oil is greater than a certain fixed value W 2 The fan is turned on. The existing control strategy of the cooling fan does not consider factors such as load rate of working conditions and environmental temperature, the setting of the opening and closing temperature is determined by the experience of a user, the opening and closing temperature can not be adjusted in real time, the problem that the working efficiency of a hydraulic oil cooling system is not high exists, the duration of hydraulic oil in the optimal working temperature range is not ideal, the system performance and the service life of components of a hydraulic system are influenced, and the aging of sealing elements, pipelines and the like can be easily caused if the temperature of the hydraulic oil is too high.
To solve the above problems, fig. 1 schematically illustrates a flow chart of a control method for a hydraulic oil cooling system according to an embodiment of the present invention. As shown in fig. 1, in an embodiment of the present invention, a control method for a hydraulic oil cooling system is provided, which is applied to a device including an engine and the hydraulic oil cooling system, where the hydraulic oil cooling system includes a cooling fan, and an operating state of the cooling fan includes an on state and an off state, and is described by taking as an example a processor applied to the device, where the control method may include the following steps:
step S102, acquiring relevant data of the equipment in a preset time period, wherein the relevant data comprises hydraulic oil temperature, environment temperature and engine load rate.
It will be appreciated that the predetermined time period is a predetermined time period, for example 30 minutes, during which the relevant data is sampled. The related data is related detection data, related job data and the like of the equipment in the process of the job. The engine load factor is a ratio of an actual operating load to a rated load of the engine.
Specifically, the processor may acquire data related to the device for a preset time period (e.g., 30 minutes), where the data may include a hydraulic oil temperature, an ambient temperature, and an engine load factor, further, the hydraulic oil temperature may be detected by a temperature detection device (e.g., a temperature sensor) that detects the hydraulic oil temperature, the ambient temperature may be detected by a temperature detection device (e.g., a temperature sensor) that detects the ambient temperature, and the engine load factor may be acquired by acquiring data output by the engine or may be calculated based on the engine torque and the engine speed, that is, the processor may acquire the hydraulic oil temperature detected by the corresponding temperature detection device, the ambient temperature, and the engine load factor output by the engine or the engine load factor calculated based on the engine torque and the engine speed.
Step S104, inputting the relevant data, a pre-stored upper limit value of the target hydraulic oil temperature and a pre-trained lower limit value of the target hydraulic oil temperature into a first temperature prediction model and a second temperature prediction model to obtain a first time length corresponding to the first temperature prediction model and a second time length corresponding to the second temperature prediction model, wherein the first temperature prediction model is a temperature prediction model of the cooling fan in an opening state, and the second temperature prediction model is a temperature prediction model of the cooling fan in a closing state.
It can be understood that the upper limit value of the target hydraulic oil temperature is an upper limit temperature value of a preset optimal oil temperature range, the lower limit value of the target hydraulic oil temperature is a lower limit temperature value of the preset optimal oil temperature range, and the specific optimal oil temperature range can be set according to actual conditions or system parameters. The first temperature prediction model is a relation model between relevant data and time of a pre-trained cooling fan in an opening state and predicted hydraulic oil temperature, and the second temperature prediction model is a relation model between relevant data and time of a pre-trained cooling fan in a closing state and predicted hydraulic oil temperature. The first time duration is the difference of time values respectively output by the first temperature prediction model based on the upper limit value and the lower limit value of the target hydraulic oil temperature, and the first time duration is the difference of time values respectively output by the second temperature prediction model based on the upper limit value and the lower limit value of the target hydraulic oil temperature.
Specifically, the processor may input relevant data (including a hydraulic oil temperature, an ambient temperature, and an engine load rate within a preset time period) and pre-stored upper limit value and lower limit value of the target hydraulic oil temperature into the first temperature prediction model and the second temperature prediction model trained in advance to obtain a first duration corresponding to the first temperature prediction model and a second duration corresponding to the second temperature prediction model.
In an embodiment, fig. 2 schematically illustrates a flowchart of the step of obtaining the first time duration and the second time duration in an embodiment of the present invention, and as shown in fig. 2, inputting the related data and the pre-stored upper limit value and the pre-stored lower limit value of the target hydraulic oil temperature into the first temperature prediction model and the second temperature prediction model trained in advance to obtain the first time duration corresponding to the first temperature prediction model and the second time duration corresponding to the second temperature prediction model, the step may include the following steps:
step S202, inputting the relevant data and a pre-stored upper limit value of the target hydraulic oil temperature into a first temperature prediction model and a second temperature prediction model which are trained in advance to obtain a first upper limit time value output by the first temperature prediction model and a second upper limit time value output by the second temperature prediction model.
It can be understood that the first upper limit time value is a larger value of the two time endpoint data corresponding to the first time length, that is, the time corresponding to the upper limit value of the temperature of the target hydraulic oil by the first temperature prediction model, and the second upper limit time value is a larger value of the two time endpoint data corresponding to the second time length, that is, the time corresponding to the upper limit value of the temperature of the target hydraulic oil by the second temperature prediction model.
Specifically, the processor inputs the relevant data and a pre-stored target hydraulic oil temperature upper limit value as input values into a first temperature prediction model and a second temperature prediction model which are trained in advance, and obtains a first upper limit time value output by the first temperature prediction model and a second upper limit time value output by the second temperature prediction model.
Step S204, inputting the relevant data and a pre-stored target hydraulic oil temperature lower limit value into a pre-trained first temperature prediction model and a pre-trained second temperature prediction model to obtain a first lower limit time value output by the first temperature prediction model and a second lower limit time value output by the second temperature prediction model.
It can be understood that the first lower limit time value is a smaller value of the two time endpoint data corresponding to the first time length, that is, a time corresponding to the lower limit value of the target hydraulic oil temperature by the first temperature prediction model, and the second lower limit time value is a smaller value of the two time endpoint data corresponding to the second time length, that is, a time corresponding to the lower limit value of the target hydraulic oil temperature by the second temperature prediction model.
Specifically, the processor inputs the relevant data and a pre-stored target hydraulic oil temperature lower limit value as input values into a first temperature prediction model and a second temperature prediction model which are trained in advance, and obtains a first lower limit time value output by the first temperature prediction model and a second lower limit time value output by the second temperature prediction model.
Step S206, determining a difference between the first upper limit time value and the first lower limit time value to obtain a first duration corresponding to the first temperature prediction model.
Specifically, the processor may calculate a difference between the first upper limit time value and the first lower limit time value according to the first upper limit time value and the first lower limit time value, so as to obtain a first time duration corresponding to the first temperature prediction model, that is, a time length between the first upper limit time value and the first lower limit time value.
Step S208, determining a difference between the second upper limit time value and the second lower limit time value to obtain a second duration corresponding to the second temperature prediction model.
Specifically, the processor may calculate a difference between the second upper limit time value and the second lower limit time value according to the second upper limit time value and the second lower limit time value, so as to obtain a second time duration corresponding to the second temperature prediction model, that is, a time length between the second upper limit time value and the second lower limit time value.
Step S104 is followed by step S106 of controlling the operating state of the cooling fan according to the first duration and the second duration.
Specifically, the processor may determine the current operating state of the cooling fan and/or the operating state within a future time period according to the first time period and the second time period, so as to control the cooling fan to be in the current operating state and/or keep the operating state unchanged within the future time period.
In one embodiment, controlling the operating state of the heat dissipation fan according to the first time period and the second time period may include: and controlling the working state of the cooling fan to be in a closed state under the condition that the first time length is less than the second time length.
Specifically, the processor may compare the first duration with the second duration, and when it is determined that the first duration is less than the second duration, that is, the time length that the operating state of the cooling fan is in the on state and the hydraulic oil is in the optimal operating temperature range (interval) is less than the time length that the operating state of the cooling fan is in the off state and the hydraulic oil is in the optimal operating temperature range (interval), at this time, in order to increase the operating time ratio of the hydraulic oil in the optimal operating temperature range (interval), the operating state of the cooling fan may be controlled to be in the off state, and further, the processor may control the cooling fan to be in the off state at the current operating state or to keep the off state in a certain time period in the future.
In one embodiment, controlling the operating state of the heat dissipation fan according to the first time period and the second time period may include: and controlling the working state of the cooling fan to be an opening state under the condition that the first duration is greater than or equal to the second duration.
Specifically, the processor may compare the first duration with the second duration, and when it is determined that the first duration is greater than or equal to the second duration, that is, the time length indicating that the operating state of the cooling fan is in the on state and the hydraulic oil is in the optimal operating temperature range (interval) is greater than or equal to the time length indicating that the operating state of the cooling fan is in the off state and the hydraulic oil is in the optimal operating temperature range (interval), at this time, in order to increase the operating time ratio of the hydraulic oil in the optimal operating temperature range (interval), the operating state of the cooling fan may be controlled to be in the on state. Further, the processor may control the cooling fan to be turned on at the current operating state or to be kept on for a certain period of time in the future.
In the embodiment of the invention, the opening and closing time of the cooling fan can be calculated and controlled in real time by comparing the time lengths of the first temperature prediction model and the second temperature prediction model in the optimal temperature interval, namely the first time length and the second time length, so that the intelligent control of the opening and closing of the cooling fan is realized, and the working time ratio of the hydraulic oil in the optimal oil temperature interval is improved under the condition of not changing hardware.
According to the control method for the hydraulic oil cooling system, the relevant data of the equipment in the preset time period are obtained, and the relevant data, the pre-stored upper limit value of the target hydraulic oil temperature and the pre-stored lower limit value of the target hydraulic oil temperature are input into the pre-trained first temperature prediction model and the pre-trained second temperature prediction model to obtain the first time length corresponding to the first temperature prediction model and the second time length corresponding to the second temperature prediction model, so that the working state of the cooling fan is controlled according to the first time length and the second time length. According to the method, under the condition that hardware is not changed, factors such as load rate of working conditions and ambient temperature are considered, the temperature prediction model related to the hydraulic oil is established in advance, intelligent control over opening or closing of the cooling fan is achieved based on the temperature prediction model, the working state of the cooling fan is controlled according to the first duration corresponding to the first temperature prediction model and the second duration corresponding to the second temperature prediction model, the time ratio of the hydraulic oil in the optimal working temperature interval can be increased, the working efficiency of a hydraulic oil cooling system is improved, the fault rate of the hydraulic system is reduced, and the service life of components of the hydraulic system is prolonged.
In one embodiment, the control method for a hydraulic oil heat dissipation system may further include: and under the condition that the current hydraulic oil temperature at the current moment is in the interval of the target hydraulic oil temperature lower limit value and the target hydraulic oil temperature upper limit value, determining a first lower limit time value and a second lower limit time value as the current moment.
Specifically, the processor may obtain a current hydraulic oil temperature at a current time in the relevant data within a preset time period, compare the current hydraulic oil temperature with a target hydraulic oil temperature lower limit value and a target hydraulic oil temperature upper limit value, and when it is determined that the current hydraulic oil temperature is located in a temperature interval where the target hydraulic oil temperature lower limit value and the target hydraulic oil temperature upper limit value are located, that is, when the current hydraulic oil temperature is greater than or equal to the target hydraulic oil temperature lower limit value and less than or equal to the target hydraulic oil temperature upper limit value, the processor may directly determine that the first lower limit time value and the second lower limit time value are time information corresponding to the current time.
In one embodiment, the control method for a hydraulic oil cooling system may further include: in a case where the first upper limit time value is infinity, the first time period is determined to be infinity.
It can be understood that when the first upper limit time value output by the first temperature prediction model is approaching infinity, which means that when the radiator fan is in the on state, the hydraulic oil temperature will not be equal to the target hydraulic oil temperature upper limit value, but will only be infinitely close to the target hydraulic oil temperature upper limit value, and at this time, the first duration can be unambiguously determined to be infinity.
In one embodiment, the control method for a hydraulic oil cooling system may further include: in a case where the second upper limit time value is infinity, the second time period is determined to be infinity.
It is understood that when the second upper time limit outputted by the second temperature prediction model is approaching infinity, which means that when the cooling fan is in the off state, the hydraulic oil temperature will not be equal to the target hydraulic oil temperature upper limit, but will only approach the target hydraulic oil temperature upper limit indefinitely, and at this time, the second duration can be unambiguously determined to be infinity.
In one embodiment, the control method for the hydraulic oil heat dissipation system may further include at least one of: determining the minimum value of the plurality of first upper limit time values as a final first upper limit time value under the condition that the number of the first upper limit time values is multiple; determining the minimum value of the plurality of first lower time values as the final first lower time value under the condition that the number of the first lower time values is multiple; determining the minimum value of the plurality of second upper limit time values as a final second upper limit time value under the condition that the number of the second upper limit time values is multiple; and determining the minimum value of the plurality of second lower limit time values as the final second lower limit time value when the number of the second lower limit time values is multiple.
It is to be understood that, when the number of at least one of the first upper time limit value, the first lower time limit value, the second upper time limit value and the second lower time limit value is multiple, that is, when the first temperature prediction model and/or the second temperature prediction model outputs multiple solutions, the processor may determine a solution with the smallest value among the multiple solutions as a final corresponding time value.
In one example, in a case where the number of the first upper time limit values is plural, the processor may determine that a smallest value among the plural first upper time limit values is a final first upper time limit value.
In one example, in a case where the number of the first lower time limit values is plural, the processor may determine that a smallest value among the plural first lower time limit values is a final first lower time limit value.
In one example, in a case where the number of the second upper time limit values is plural, the processor may determine that a smallest value among the plural second upper time limit values is a final second upper time limit value.
In one example, in a case where the number of the second lower time limit values is plural, the processor may determine that a smallest value among the plural second lower time limit values is a final second lower time limit value.
In one embodiment, the obtaining of the first temperature prediction model and the second temperature prediction model may include: acquiring historical related data of equipment in an open state and historical related data of the equipment in a closed state; based on a deep neural network algorithm, respectively training according to historical operation data in an open state and historical related data in a closed state to obtain a first temperature prediction model and a second temperature prediction model.
It is understood that the historical related data is related detection data and related operation data of the equipment in the process of operation in a long time (for example, 1 year) in the past, and can comprise data such as hydraulic oil temperature, ambient temperature and engine load rate.
Specifically, the processor may obtain historical related data of the device in an on state and historical related data of the device in an off state, and train according to the historical related data of the cooling fan in the on state to obtain parameters of the first temperature prediction model based on a deep neural network algorithm, train according to the historical related data of the cooling fan in the off state to obtain parameters of the second temperature prediction model, thereby obtaining the first temperature prediction model and the second temperature prediction model trained in advance. For example, assume that the first temperature prediction model (or the second temperature prediction model) is: y is 1 =(α 1 A 1 +α 2 A 2 +α 2 A 2 ) t + b, then y therein 1 The predicted hydraulic oil temperature, A, which may represent a first temperature prediction model (or a second temperature prediction model) 1 ,A 2 ,A 3 Individual watchHydraulic oil temperature, ambient temperature and engine load rate data shown over a predetermined period of time, t may represent time, α 1 ,α 2 ,α 3 And b may represent a parameter of the first temperature prediction model (or the second temperature prediction model).
In some embodiments, the processor may obtain the stored state information of the heat dissipation fan and the historical related data of the equipment from the database, so that the first temperature prediction model and the second temperature prediction model can be trained according to the state information of the heat dissipation fan and the historical related data of the equipment based on a deep neural network algorithm.
In one embodiment, the device may further comprise an actuator; the historical related data and related data may further include at least one of an action state data of the actuator, an action intensity data of the actuator, an action time of the actuator, a torque of the engine, and a rotational speed of the engine.
It is understood that the executing structure may include, but is not limited to, a main winch, an auxiliary winch, a slewing device, an arm support, and the like, and further, the motion state data of the executing mechanism may include, but is not limited to, a main winch motion, an auxiliary winch motion, a slewing motion, a luffing motion, a main arm telescoping motion, and the like.
In the embodiment of the invention, the first temperature prediction model and the second temperature prediction model can be related to other factors except the hydraulic oil temperature, the ambient temperature and the engine load rate, so that the accuracy of the temperature prediction models can be improved.
In a specific embodiment of the present invention, the control method for the hydraulic oil cooling system can be divided into two stages: 1. performing offline hydraulic oil temperature modeling based on big data analysis; 2. and (4) online intelligent control of the startup and shutdown of the hydraulic oil cooling fan.
Hydraulic oil temperature modeling based on big data analysis
Taking a crane as an example for explanation, when the crane works, the crane returns relevant state information and sensor data to the internet of things big data platform, and the obtained data types are (without being limited to): ambient temperature, hydraulic oil temperature, engine torque and rotation speed, opening and closing states of a cooling fan, action states of an actuating mechanism (main hoisting action, auxiliary hoisting action, rotation action, amplitude change action, main arm stretching action) and the like.
Through accumulation of historical data, a large amount of operation data of a plurality of cranes is stored in the Internet of things big data platform. Through a machine learning method, a hydraulic oil temperature rise characteristic curve (comprising a first temperature prediction model and a second temperature prediction model) is obtained through training from historical data, namely a relation model among data such as hydraulic oil temperature, environment temperature and engine load factor is as follows:
(1) when the fan is in an on state (where on represents the fan is on), the hydraulic oil temperature rise characteristic curve (i.e. the first temperature prediction model) is: f. of on (A 1 ,A 2 ,A 3 ,t)。
(2) When the fan is in the off state (where off represents the fan off), the hydraulic oil temperature rise characteristic curve (i.e. the second temperature prediction model) is: f. of off (A 1 ,A 2 ,A 3 ,t)。
Wherein t represents time, A 1 ,A 2 ,A 3 Respectively represent in [ t 0 -T,t 0 ]Hydraulic oil temperature, ambient temperature, and engine load rate data over a period of time. t is t 0 Representing the current time and T representing the length of the time period.
Intelligent control for turning on and off hydraulic oil cooling fan
Fig. 3 schematically shows a flow chart of a control method for a hydraulic oil cooling system according to another embodiment of the present invention. As shown in fig. 3, for the convenience of explaining the intelligent control process, the following notation is adopted: at the current moment: t is t 0 ;t 0 Oil temperature at the moment: w; the optimal oil temperature range is as follows: [ W ] 1 ,W 2 ],W 1 Is the target hydraulic oil temperature lower limit value, W 2 The temperature is the upper limit value of the target hydraulic oil temperature; the state of the heat radiation fan: off represents off, on represents on; the state switching time of the cooling fan is as follows: Δ T, represents the minimum unit of time to maintain the state if switched from on to off, or off to on.
The basic principle of the intelligent control process is as follows: respectively calculating the hydraulic oil temperature rise characteristic curves (namely a first temperature prediction model and a second temperature prediction model) of the cooling fan in the on state and the off state every delta T time by a processor or a controller (for example, an on-board controller), and then respectively calculating f on (A 1 ,A 2 ,A 3 T) curve (i.e. first temperature prediction model) at [ W 1 ,W 2 ]Length of time of, and f off (A 1 ,A 2 ,A 3 T) curve (i.e. second temperature prediction model) at [ W 1 ,W 2 ]The time length of the cooling fan is compared with the time length of the cooling fan in the optimal temperature interval, the opening and closing time of the cooling fan is calculated and controlled in real time, and the intelligent control of the opening and closing of the fan is achieved, so that the working time of the hydraulic oil in the optimal oil temperature interval is improved under the condition that hardware is not changed.
Fig. 4 schematically shows a diagram of prediction curves of the first temperature prediction model and the second temperature prediction model in an embodiment of the invention. Fig. 5 schematically shows a diagram of prediction curves of the first temperature prediction model and the second temperature prediction model in another embodiment of the present invention. FIG. 6 is a schematic diagram illustrating the prediction curves of the first temperature prediction model and the second temperature prediction model in another embodiment of the present invention. Fig. 7 schematically shows a diagram of prediction curves of the first temperature prediction model and the second temperature prediction model in another embodiment of the present invention. The following control strategies for different situations are presented by way of example:
case 1: current time t 0 Oil temperature W of<W 1 Separately calculate f on (A 1 ,A 2 ,A 3 T) and f off (A 1 ,A 2 ,A 3 T), as shown in fig. 4:
f on (A 1 ,A 2 ,A 3 t) is in [ W 1 ,W 2 ]The time length of (c) is: DTon ton 2-ton 1.
f off (A 1 ,A 2 ,A 3 T) is in [ W 1 ,W 2 ]The time length of (c) is: DToff is toff 2-toff 1.
If DToff > DTon, i.e. the second time period is greater than the first time period, the fan state is switched to off state, otherwise the fan state is switched to on state.
Case 2: current time t 0 Oil temperature W 1 ≤W≤W 2 Separately calculate f on (A 1 ,A 2 ,A 3 T) and f off (A 1 ,A 2 ,A 3 T), as shown in fig. 5:
f on (A 1 ,A 2 ,A 3 t) is in [ W 1 ,W 2 ]The time length of (A) is as follows: DTon ton 1-t 0 。
f off (A 1 ,A 2 ,A 3 T) is in [ W 1 ,W 2 ]The time length of (c) is: DToff 1-t 0 。
If DToff > DTon, i.e. the second time period is greater than the first time period, the fan state is switched to off state, otherwise the fan state is switched to on state.
Case 3: current time t 0 Oil temperature W 1 ≤W≤W 2 Separately calculate f on (A 1 ,A 2 ,A 3 T) and f off (A 1 ,A 2 ,A 3 T), as shown in fig. 6:
f on (A 1 ,A 2 ,A 3 t) is in [ W 1 ,W 2 ]The time length of (A) is as follows: DTon ═ infinity.
f off (A 1 ,A 2 ,A 3 T) is in [ W 1 ,W 2 ]The time length of (A) is as follows: DToff 1-t 0 。
At this time, the first time period (∞) is longer than the second time period, and the fan state is switched to the on state.
Case 4: current time t 0 Oil temperature W 1 ≤W≤W 2 Separately calculate f on (A 1 ,A 2 ,A 3 T) and f off (A 1 ,A 2 ,A 3 T), as shown in fig. 7:
f on (A 1 ,A 2 ,A 3 t) is in [ W 1 ,W 2 ]The time length of (c) is: DTon ton 1-t 0 。
f off (A 1 ,A 2 ,A 3 T) is in [ W 1 ,W 2 ]The time length of (A) is as follows: DToff 1-t 0 。
If DToff > DTon, i.e. the second time period is greater than the first time period, the fan state is switched to off state, otherwise the fan state is switched to on state.
Case 5: current time t 0 Oil temperature W>W 2 At this time, the fan state is switched to the on state.
Understandably, under the condition that the current hydraulic oil temperature value is determined to be larger than the upper limit value of the target hydraulic oil temperature, the processor can control the working state of the cooling fan to be the starting state.
According to the control method for the hydraulic oil cooling system, provided by the embodiment of the invention, under the condition that hardware is not changed, compared with the prior art, the hydraulic oil temperature prediction model is established in a mode of carrying out big data analysis on historical operating condition data, the intelligent control of the opening/closing of the cooling fan is realized based on the prediction model, namely the intelligent control of the fan on-off decision is carried out based on the duration of a predicted temperature rise curve in an optimal oil temperature range, the time occupation ratio of hydraulic oil in an optimal working temperature range is increased, the faults of the hydraulic system are reduced, the service life of components of the hydraulic system is prolonged, and the working efficiency of the hydraulic oil cooling system is further improved.
Fig. 8 is a block diagram schematically showing a control device for a hydraulic oil cooling system according to an embodiment of the present invention. As shown in fig. 8, in an embodiment of the present invention, there is provided a control device for a hydraulic oil cooling system, including: hydraulic oil temperature check out test set 810, ambient temperature check out test set 820 and processor 830, wherein:
a hydraulic oil temperature detection device 810 configured to detect a hydraulic oil temperature.
Understandably, the hydraulic oil temperature detecting device 810 may be disposed inside a hydraulic system of the device for detecting the hydraulic oil temperature.
An ambient temperature detection device 820 configured to detect an ambient temperature.
Understandably, the ambient temperature sensing device 820 may be provided on a device, such as a body of a crane, for sensing the ambient temperature.
A processor 830 configured to: acquiring relevant data of equipment in a preset time period, wherein the relevant data comprises hydraulic oil temperature, environment temperature and engine load rate; inputting relevant data and pre-stored upper limit value and lower limit value of the target hydraulic oil temperature into a first temperature prediction model and a second temperature prediction model which are trained in advance to obtain a first time length corresponding to the first temperature prediction model and a second time length corresponding to the second temperature prediction model, wherein the first temperature prediction model is a temperature prediction model of a cooling fan in an on state, and the second temperature prediction model is a temperature prediction model of the cooling fan in an off state; and controlling the working state of the cooling fan according to the first time length and the second time length.
According to the control device for the hydraulic oil cooling system, the relevant data of the equipment in the preset time period are obtained, and then the relevant data, the pre-stored upper limit value of the target hydraulic oil temperature and the pre-stored lower limit value of the target hydraulic oil temperature are input into the pre-trained first temperature prediction model and the pre-trained second temperature prediction model, so that the first duration corresponding to the first temperature prediction model and the second duration corresponding to the second temperature prediction model are obtained, and the working state of the cooling fan is controlled according to the first duration and the second duration. Under the condition that hardware is not changed, factors such as load rate of working conditions and ambient temperature are considered, a temperature prediction model related to hydraulic oil is established in advance, intelligent control over opening or closing of a cooling fan is achieved based on the temperature prediction model, the working state of the cooling fan is controlled according to first duration corresponding to the first temperature prediction model and second duration corresponding to the second temperature prediction model, the time ratio of the hydraulic oil in an optimal working temperature interval can be increased, the working efficiency of a hydraulic oil cooling system is improved, the fault rate of a hydraulic system is reduced, and the service life of components of the hydraulic system is prolonged.
In one embodiment, the processor 830 is further configured to: inputting the relevant data and a pre-stored target hydraulic oil temperature upper limit value into a pre-trained first temperature prediction model and a pre-trained second temperature prediction model to obtain a first upper limit time value output by the first temperature prediction model and a second upper limit time value output by the second temperature prediction model; inputting the relevant data and a pre-stored target hydraulic oil temperature lower limit value into a first temperature prediction model and a second temperature prediction model which are trained in advance to obtain a first lower limit time value output by the first temperature prediction model and a second lower limit time value output by the second temperature prediction model; determining the difference between the first upper limit time value and the first lower limit time value to obtain a first duration corresponding to the first temperature prediction model; and determining the difference between the second upper limit time value and the second lower limit time value to obtain a second time length corresponding to the second temperature prediction model.
In one embodiment, the processor 830 is further configured to: and under the condition that the current hydraulic oil temperature at the current moment is in the interval where the target hydraulic oil temperature lower limit value and the target hydraulic oil temperature upper limit value are located, determining the first lower limit time value and the second lower limit time value as the current moment.
In one embodiment, processor 830 is further configured to: in a case where the first upper limit time value is infinity, the first time period is determined to be infinity.
In one embodiment, the processor 830 is further configured to: in a case where the second upper limit time value is infinity, the second time period is determined to be infinity.
In one embodiment, the processor 830 is further configured to at least one of: under the condition that the number of the first upper limit time values is multiple, determining the minimum value in the multiple first upper limit time values as a final first upper limit time value; determining the minimum value of the plurality of first lower time values as the final first lower time value under the condition that the number of the first lower time values is multiple; determining the minimum value of the plurality of second upper limit time values as a final second upper limit time value under the condition that the number of the second upper limit time values is multiple; and determining the minimum value of the plurality of second lower limit time values as the final second lower limit time value when the number of the second lower limit time values is multiple.
In one embodiment, the processor 830 is further configured to: and controlling the working state of the cooling fan to be in a closing state under the condition that the first time length is less than the second time length.
In one embodiment, the processor 830 is further configured to: and controlling the working state of the cooling fan to be an opening state under the condition that the first duration is greater than or equal to the second duration.
In one embodiment, the processor 830 is further configured to: acquiring historical related data of equipment in an open state and historical related data of the equipment in a closed state of a cooling fan; based on a deep neural network algorithm, respectively training according to historical operation data in an open state and historical related data in a closed state to obtain a first temperature prediction model and a second temperature prediction model.
In one embodiment, the apparatus further comprises an actuator; the historical related data and the related data further include at least one of operating state data of the actuator, operating intensity data of the actuator, operating time of the actuator, torque of the engine, and rotational speed of the engine.
An embodiment of the present invention provides a processor configured to execute the control method for a hydraulic oil heat dissipation system according to the above.
The embodiment of the invention provides a hydraulic oil cooling system, which comprises: a heat-dissipating fan; and the control device for the hydraulic oil cooling system is used.
An embodiment of the present invention provides an apparatus, including: an engine; and according to the hydraulic oil cooling system.
In one embodiment, the apparatus comprises a crane.
The preferred embodiments of the present invention have been described in detail with reference to the accompanying drawings, however, the present invention is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present invention within the technical idea of the present invention, and these simple modifications all fall within the protection scope of the present invention.
It should be noted that the various features described in the above embodiments may be combined in any suitable manner without departing from the scope of the invention. The invention is not described in detail in order to avoid unnecessary repetition.
In addition, any combination of the various embodiments of the present invention is also possible, and the same should be considered as the disclosure of the present invention as long as it does not depart from the spirit of the present invention.