A method and device for identifying the steering of a vehicle mixing drum and an engineering vehicle

Abstract

The present invention relates to the field of feedback on the rotation state of a mixing drum, and particularly to a method and device for identifying the steering of a mixing drum of a vehicle and an engineering vehicle. A prediction model is constructed based on historical working condition data of the vehicle and mixing drum steering data; current working condition data of the vehicle is obtained; the current working condition data is input into the prediction model; a prediction result output by the prediction model is obtained, and the current rotation state of the mixing drum corresponds to the current working condition data in terms of time; and current steering data of the mixing drum is generated according to the prediction result. This application does not rely on monitoring data obtained by a specific sensor for monitoring the steering of the drum body to determine the steering of the mixing drum, but predicts and determines the forward and reverse rotation of the mixing drum by using the current working condition data of the mixer truck. Thus, the problem in the prior art that the steering data of the mixing drum is often missing due to the inability to install a sensor or damage to the sensor is solved.

Description

Technical Field

[0001] The present application relates to the field of feedback on the rotation state of a mixing drum, and specifically relates to a method and device for identifying the steering of a vehicle mixing drum and an engineering vehicle. Background Art

[0002] In order to ensure the physical properties of concrete, the mixing drum loaded with concrete will maintain rotation during transportation, generally in the forward rotation direction. During the unloading process, the mixing drum generally rotates in the reverse direction. Through the reverse rotation of the mixing drum, a reverse conveying force is generated by the spiral agitator in the mixing drum. Under the action of this reverse conveying force, the concrete in the mixing drum is pushed out to complete the unloading work.

[0003] In the prior art, the rotation state of the mixing drum is generally monitored by a sensor installed on the mixing drum. However, it is difficult to install a sensor on the existing mixing drum, and the sensor is vulnerable to structural damage. Moreover, some old models of mixer trucks cannot install sensors, resulting in frequent missing of the steering data of the mixing drums on many existing mixer trucks, which has a great impact on the intelligent application development based on the collaborative operation of concrete production plants, mixer trucks, and construction sites. Summary of the Invention

[0004] In view of this, the present application provides a method and device for identifying the steering of a vehicle mixing drum and an engineering vehicle, which solve the technical problem of frequent missing of the steering data of the mixing drum in the prior art.

[0005] According to one aspect of the present application, there is provided a method for identifying the steering of a vehicle mixing drum, including:

[0006] Constructing a prediction model based on vehicle historical working condition data and mixing drum steering data;

[0007] Obtaining the current working condition data of the vehicle;

[0008] Inputting the current working condition data into the prediction model;

[0009] Obtaining a prediction result output by the prediction model, where the prediction result includes the current rotation state of the mixing drum of the vehicle, and the current rotation state of the mixing drum corresponds to the current working condition data in terms of time; and

[0010] Generating the current steering data of the mixing drum according to the prediction result.

[0011] In a possible implementation manner, generating the current steering data of the mixing drum of the vehicle according to the prediction result includes:

[0012] When the prediction result is that the current rotation state of the mixing drum is reverse, assign the steering determination parameter a value equal to the sum of a preset value and a first value, where the first value is the value assigned to the previous steering determination parameter of the mixing drum, and the value assigned to the previous steering determination parameter of the mixing drum corresponds to the previous working condition data of the mixing drum. The previous working condition data and the current working condition data are arranged in chronological order.

[0013] When the steering determination parameter is greater than or equal to a threshold value, the current steering data of the mixing drum is reverse.

[0014] In a possible implementation, generating the current steering data of the mixing drum of the vehicle according to the prediction result includes:

[0015] When the steering determination parameter is less than the threshold value, the current steering data of the mixing drum is forward.

[0016] In a possible implementation, generating the current steering data of the mixing drum of the vehicle according to the prediction result includes:

[0017] When the prediction result is that the current rotation state of the mixing drum is forward, the current steering data of the mixing drum is forward.

[0018] In a possible implementation, constructing the prediction model includes:

[0019] Construct an initial prediction model;

[0020] Obtain multiple sets of historical working condition data and the steering data of the mixing drum at the corresponding moments of the historical working condition data. Each set of historical working condition data includes multiple fields, and each field corresponds to monitoring data;

[0021] Perform data processing on the historical working condition data and the steering data of the mixing drum to generate a sample data set; and

[0022] Input the data in the sample data set into the initial prediction model for training.

[0023] In a possible implementation, performing data processing on the historical working condition data and the steering data of the mixing drum to generate a sample data set includes:

[0024] Search for the fields in the historical working condition data where the monitoring data is a null value;

[0025] Fill the fields with null monitoring data to generate first training sub-data;

[0026] Among them, the sample data set includes multiple first training sub-data.

[0027] In a possible implementation, data processing is performed on the historical working condition data and the mixing drum steering data to generate a sample data set, including:

[0028] Search for noise fields in the historical working condition data;

[0029] Remove the noise fields.

[0030] In a possible implementation, after obtaining the current working condition data of the vehicle, the vehicle mixing drum steering recognition method further includes:

[0031] Search for fields with null monitoring data in the current working condition data;

[0032] Fill the fields with null monitoring data.

[0033] In a possible implementation, after generating the current steering data of the mixing drum according to the prediction result, the vehicle mixing drum steering recognition method further includes:

[0034] Obtain first steering data, where the first steering data includes the steering data of the mixing drum obtained by a steering sensor;

[0035] Compare the current steering data with the first steering data to generate a steering comparison result;

[0036] When the steering comparison result indicates that the steering information represented by the current steering data is consistent with the first steering data, use the current steering data as the actual steering result of the mixing drum.

[0037] According to the second aspect of the present application, the present application further provides a vehicle mixing drum steering recognition device, including:

[0038] A model construction module for constructing a prediction model based on vehicle historical working condition data and mixing drum steering data;

[0039] A data acquisition module for acquiring the current working condition data of the vehicle;

[0040] A data input module for inputting the working condition data into the prediction model;

[0041] An identification module for obtaining the prediction result output by the prediction model, where the prediction result includes the current rotation state of the mixing drum of the vehicle, and the current rotation state of the mixing drum corresponds to the current working condition data in time; and generating the current steering data of the mixing drum according to the prediction result.

[0042] According to the third aspect of the present application, the present application further provides an engineering vehicle, including:

[0043] A mixing drum; and

[0044] The vehicle mixing drum steering recognition device described above.

[0045] A vehicle mixing drum steering recognition method provided by this application uses historical working condition data and mixing drum steering data to establish a prediction model for the forward and reverse states of the concrete mixing drum based on the real-time working condition data of the vehicle. By inputting the currently obtained real-time working condition data of the vehicle into the prediction model, the prediction result of the mixing drum steering is obtained, and then the current steering data of the mixing drum is obtained through the processing of the prediction result. This application does not rely on the monitoring data obtained by a specific sensor for monitoring the steering of the drum body to judge the steering of the mixing drum, but predicts and judges the forward and reverse rotation of the mixing drum by using the current working condition data of the mixer truck. Thus, it solves the problem in the prior art that the steering data of the mixing drum is often missing due to the inability to install sensors or sensor damage. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] By describing the embodiments of this application in more detail in combination with the drawings, the above and other objects, features, and advantages of this application will become more obvious. The drawings are used to provide a further understanding of the embodiments of this application and constitute a part of the specification, and are used to explain this application together with the embodiments of this application, and do not constitute a limitation to this application. In the drawings, the same reference numerals generally represent the same components or steps.

[0047] Figure 1 The figure shows a schematic flow chart of a vehicle mixing drum steering recognition method provided by an embodiment of this application.

[0048] Figure 2 The figure shows a schematic flow chart of a vehicle mixing drum steering recognition method provided by another embodiment of this application.

[0049] Figure 3 The figure shows a schematic flow chart of a vehicle mixing drum steering recognition method provided by another embodiment of this application.

[0050] Figure 4 The figure shows a schematic flow chart of a vehicle mixing drum steering recognition method provided by another embodiment of this application.

[0051] Figure 5 The figure shows a schematic flow chart of a vehicle mixing drum steering recognition method provided by another embodiment of this application.

[0052] Figure 6 The figure shows a schematic flow chart of a vehicle mixing drum steering recognition method provided by another embodiment of this application.

[0053] Figure 7The figure shows a schematic flowchart of constructing a prediction model in a method for identifying the steering of a vehicle mixing drum provided by another embodiment of the present application.

[0054] Figure 8 The figure shows a schematic flowchart of constructing a prediction model in a method for identifying the steering of a vehicle mixing drum provided by another embodiment of the present application.

[0055] Figure 9 The figure shows a schematic flowchart of constructing a prediction model in a method for identifying the steering of a vehicle mixing drum provided by another embodiment of the present application.

[0056] Figure 10 The figure shows a schematic flowchart of constructing a prediction model in a method for identifying the steering of a vehicle mixing drum provided by another embodiment of the present application.

[0057] Figure 11 The figure shows a schematic flowchart of constructing a prediction model in a method for identifying the steering of a vehicle mixing drum provided by another embodiment of the present application.

[0058] Figure 12 The figure shows a schematic flowchart of constructing a prediction model in a method for identifying the steering of a vehicle mixing drum provided by another embodiment of the present application.

[0059] Figure 13 The figure shows a schematic structural diagram of a device for identifying the steering of a vehicle mixing drum provided by another embodiment of the present application.

[0060] Figure 14 The figure shows a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0061] In the description of the present application, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically defined. In all the directional indications (such as up, down, left, right, front, back, top, bottom...) in the embodiments of the present application, they are only used to explain the relative position relationship and movement conditions between components in a specific posture (as shown in the drawings). If the specific posture changes, the directional indications will change accordingly. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0062] In addition, the mention of "embodiment" in this document means that the specific features, structures, or characteristics described in connection with the embodiment may be included in at least one embodiment of the present application. The occurrence of this phrase at various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0063] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts belong to the scope of protection of the present application.

[0064] Overview of the Application

[0065] During the process of transporting concrete by a concrete mixer truck, the rotation of the mixing drum will be maintained to ensure the physical properties of the transported concrete. During transportation, the mixing drum generally rotates forward. During the discharging process of the mixer truck, the mixing drum generally rotates in reverse. By reversing the mixing drum, a reverse conveying force is generated by the spiral agitator in the mixing drum. Under the action of this reverse conveying force, the concrete in the mixing drum is pushed out to complete the discharging work. The forward and reverse rotation states of the concrete mixing drum of the mixer truck are key data for realizing the collaborative operation of the concrete production station, the mixer truck, and the construction site.

[0066] The main method for assisting in judging the steering state of the concrete mixing drum of the mixer truck is based on the information obtained by key sensors, such as the state of the steering operation device, the speed state of the mixing drum, etc. Based on these key feature data, the steering of the mixing drum is judged. Since the method for assisting in detecting the steering of the mixing drum depends on specific sensor data, the existing method has a higher implementation cost due to the need to install and maintain sensors, and has low applicability to old mixer trucks that cannot install relevant sensors.

[0067] Therefore, the present application provides a method for identifying the steering of a vehicle mixing drum, including:

[0068] Constructing a prediction model according to the vehicle historical working condition data and the mixing drum steering data, where the vehicle historical working condition data includes one or more of the engine speed, the torque of the upper-mounted motor, the current of the upper-mounted motor, the vehicle voltage, and the mixing drum speed;

[0069] Obtaining the current working condition data of the vehicle;

[0070] Inputting the current working condition data into the prediction model;

[0071] Obtain the prediction result output by the prediction model, where the prediction result includes the current rotation state of the mixing drum of the vehicle, and the current rotation state of the mixing drum corresponds to the current working condition data in terms of time; and

[0072] Generate the current steering data of the mixing drum according to the prediction result. This application does not rely on the monitoring data obtained by a specific sensor for monitoring the steering of the drum body to judge the steering of the mixing drum, but realizes the prediction and judgment of the forward and reverse rotation of the mixing drum by using the current working condition data of the mixer truck. After briefly introducing the implementation principle of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this application.

[0073] Exemplary Method

[0074] As Figure 1 shown, this application provides a method for identifying the steering of a vehicle mixing drum, including the following steps:

[0075] Step S10: Construct a prediction model according to the vehicle historical working condition data and the mixing drum steering data, where the vehicle historical working condition data includes one or more of engine speed, upper mounting motor torque, upper mounting motor current, vehicle voltage, and mixing drum speed;

[0076] Specifically, the constructed prediction model is used to generate a corresponding prediction result after inputting the current working condition data of the vehicle.

[0077] Step S11: Obtain the current working condition data of the vehicle;

[0078] Specifically, the working condition data generated by the vehicle at the current time point obtained at the current time point is the current working condition data of the vehicle. Each current working condition data contains multiple fields, where the fields are used to characterize the corresponding monitoring items, such as engine speed, upper mounting motor torque, upper mounting motor current, vehicle voltage, and mixing drum speed. Each field will correspond to monitoring data, and the monitoring data is used to characterize the actual value of the monitoring data detected by the monitoring item corresponding to it. For example: if the monitoring data corresponding to field A in a certain current working condition data is B, it means that when obtaining this current working condition data, the value of the monitoring data collected by monitoring item A at this time point is B.

[0079] The number and types of fields included in the obtained current working condition data are the same as the number and types of fields in the vehicle historical working condition data used to construct the prediction model.

[0080] Step S12: Input the current working condition data into the prediction model;

[0081] Specifically, the determination of the specific rotation direction of the mixing drum is usually carried out during the rotation of the mixing drum. Therefore, before determining the rotation direction of the mixing drum, it is necessary to determine whether the corresponding installed mixing drum is in a rotating state. When determining this state, a signal used to represent the rotation of the mixing drum can be received separately to determine the rotation state of the mixing drum. It is also possible to judge the on / off state of the vehicle from the monitoring data of one or several fields in the currently obtained working condition data that can indirectly reflect the rotation state of the mixing drum. For example, the monitoring data of the mixing drum rotation speed in the currently obtained working condition data can directly reflect the rotation state of the mixing drum.

[0082] Step S13: Obtain the prediction result output by the prediction model. The prediction result includes the current rotation state of the mixing drum of the vehicle, and the current rotation state of the mixing drum corresponds to the current working condition data in terms of time.

[0083] Specifically, after inputting the corresponding current working condition data into the prediction model when the vehicle is powered on, the prediction model will predict a corresponding prediction result, and the prediction result includes the current forward and reverse rotation states of the mixing drum.

[0084] Step S14: Generate the current rotation direction data of the mixing drum according to the prediction result.

[0085] A method for identifying the rotation direction of a vehicle mixing drum provided by the present application establishes a prediction model for the forward and reverse rotation states of a concrete mixing drum by using historical working condition data and mixing drum rotation direction data. By inputting the currently obtained current working condition data of the vehicle into the prediction model, the prediction result of the mixing drum rotation direction is obtained, and then the current rotation direction data of the mixing drum is obtained by processing the prediction result, thereby obtaining the rotation direction result of the mixing drum.

[0086] The present application does not rely on the monitoring data obtained by a specific sensor for monitoring the rotation direction of the mixing drum to judge the rotation direction of the mixing drum, but predicts and judges the forward and reverse rotation of the mixing drum by using the current working condition data of the mixer truck. Thus, the problem in the prior art that the rotation direction data of the mixing drum is often missing due to the inability to install a sensor or the damage of the sensor is solved.

[0087] Optionally, as Figure 2 shown, after step S11 of obtaining the current working condition data of the vehicle, the method for identifying the rotation direction of the vehicle mixing drum further includes:

[0088] Step S111: Search for the fields in the current working condition data where the monitoring data is a null value.

[0089] Step S112: Fill the fields where the monitoring data is a null value.

[0090] Search for fields in the current working condition data. When the detection data corresponding to a field in the current working condition data is a null value, then step S112: Fill in the fields with null monitoring data. The specific steps are as follows:

[0091] Step S113: According to the time point of the current working condition data, obtain multiple monitoring data generated within the first preset duration before the time point;

[0092] Step S114: Calculate the average value of the multiple monitoring data, and fill the average value into the field with the null value to generate the first current working condition data, and replace the corresponding current working condition data with the first current working condition data.

[0093] After being processed by steps S111 to S114, there are no fields with null values in the current working condition data. Thus, it makes the form of the current working condition data closer to that of the following first training sub-data for training the prediction model, and thereby can improve the accuracy of the prediction result obtained after the current working condition data is input into the prediction model.

[0094] Optionally, as Figure 3 shown, after step S11 to obtain the current working condition data of the vehicle, the vehicle mixing drum steering recognition method further includes the following steps:

[0095] Step S115: Search for fields in the current working condition data corresponding to multiple monitoring data;

[0096] Step S116: Calculate the average value of the multiple monitoring data, and replace the multiple monitoring data with the aligned monitoring data to generate the first current working condition data, and replace the corresponding current working condition data with the first current working condition data. Among them, the aligned monitoring data is the average value.

[0097] After being processed by steps S111 to S116, the generated current working condition data not only has no fields with null values, but also has no fields corresponding to multiple monitoring data. Thus, it makes the form of the current working condition data closer to that of the following first training sub-data for training the prediction model, and thereby can improve the accuracy of the prediction result obtained after the current working condition data is input into the prediction model. Of course, the processing process of steps S115 to S116 is not a necessary process. If the values of the monitoring data corresponding to the fields in the collected data are all unique, then the processing of steps S115 to S116 is not required.

[0098] In a possible implementation manner, as Figure 4 shown, step S14 to generate the current steering data of the mixing drum of the vehicle according to the prediction result specifically includes the following steps:

[0099] Step S141: When the prediction result is that the current rotation state of the mixing drum is reverse, assign a steering determination parameter a value equal to the sum of a preset value and a first value. The first value is the value assigned to the previous steering determination parameter of the mixing drum. The value assigned to the previous steering determination parameter of the mixing drum corresponds to the previous operating condition data of the mixing drum. Among them, the previous operating condition data and the current operating condition data are arranged in sequence in terms of time.

[0100] Specifically, taking the preset value as 1 for illustration, the current prediction result is reverse, and the rotation state corresponding to the previous operating condition data is reverse. At this time, the first value corresponding to the value assigned to the previous steering determination parameter of the mixing drum is 1. Then, the value assigned to the steering determination parameter corresponding to the current operating condition data is the sum of the preset value and the first value, that is, 1 + 1 = 2. When the preset value is 1, the assignment of the steering determination parameter in this example can be specifically represented by the formula CV1 = CV2 + 1. Where CV1 represents the value to be assigned to the steering determination parameter corresponding to the current operating condition data, CV2 represents the first value, and 1 represents the preset value.

[0101] Step S142: When the steering determination parameter is greater than or equal to a threshold value, generate a second value, and the second value is used to indicate that the current motion state of the mixing drum is reverse.

[0102] Specifically, in practical applications, a threshold value is set according to the actual usage scenario. When the steering determination parameter is greater than or equal to the threshold value, a second value is generated, and the second value is used to characterize that the current motion state of the mixing drum is reverse.

[0103] Since in the actual use process, the state of the mixing drum being in reverse is the discharging state, which belongs to a minority situation, and the prediction accuracy of the prediction model is not 100%, so the determination of the current motion state of the mixing drum being reverse is more stringent. That is, when the prediction result indicates that the mixing drum is reverse, it is also necessary to compare and judge the assignment of the steering determination parameter with the threshold value. Thus, it is possible to further reduce the error caused by the occasional prediction error of the prediction model, resulting in a deviation in the final determination of the current motion state of the mixing drum. Therefore, the accuracy of the current motion state information of the mixing drum finally output in this embodiment can be further improved.

[0104] In a possible implementation manner, as Figure 5 shown, step S14 generates the current steering data of the mixing drum of the vehicle according to the prediction result, which specifically includes the following steps:

[0105] Step S143: When the steering determination parameter is less than the threshold value, generate a third value, and the third value is used to indicate that the current steering data of the mixing drum is forward rotation.

[0106] Specifically, taking the preset value as 1 as an example, the assignment of the steering determination parameter in this example can be specifically expressed by the formula CV1 = CV2 + 1. Where CV1 represents the value to be assigned to the prediction result corresponding to the current working condition data, CV2 represents the first numerical value, and 1 represents the preset numerical value.

[0107] In a possible implementation manner, as Figure 6 shown, step S14 generating the current steering data of the mixing drum of the vehicle according to the prediction result specifically includes the following steps:

[0108] Step S144: When the prediction result is that the current rotation state of the mixing drum is forward rotation, generate a third numerical value, and the third numerical value is used to represent that the current steering data of the mixing drum is forward rotation.

[0109] Specifically, when the prediction result is that the current rotation state of the mixing drum is forward rotation, directly generate a third numerical value used to represent that the current motion state of the mixing drum is forward rotation.

[0110] In a possible implementation manner, as Figure 7 shown, step S10 constructing the prediction model specifically includes the following steps:

[0111] Step S101: Construct an initial prediction model;

[0112] Specifically, the initial prediction model used can be an existing integrated learning model such as random forest, xgboost, etc.; or a logistic regression model or a support vector machine model or a clustering algorithm model.

[0113] Step S102: Obtain multiple groups of historical working condition data and the steering data of the mixing drum at the corresponding moments of the historical working condition data. Each group of historical working condition data includes multiple fields, and each field corresponds to monitoring data;

[0114] Specifically, the meanings of the fields in the historical working condition data and the corresponding monitoring data are the same as those of the fields and the corresponding monitoring data in the current working condition data in step S11 above. The difference is that the historical working condition data in this step also contains a part of noise fields.

[0115] Among them, the noise fields include the following 3 types of fields:

[0116] Illustrated by the following example, if a total of 100 pieces of historical working condition data are obtained, each piece of historical working condition data contains 100 fields, and each field corresponds to a monitoring data. Therefore, in the 100 pieces of historical working condition data obtained, each field should correspond to 100 monitoring data.

[0117] When the values of the 100 monitoring data corresponding to a certain field are all null values, then this field is a noise field;

[0118] Similarly, when the ratio of the number of null values in the monitoring data corresponding to a certain field to the total number of monitoring data is greater than the threshold, then this field is a noise field;

[0119] In addition, calculate the Pearson correlation coefficient for each field based on the Pearson correlation coefficient method, where the field with a Pearson correlation coefficient lower than the threshold is a noise field.

[0120] Step S103: Process the historical operating condition data to generate a sample data set; and

[0121] Step S104: Input the data in the sample data set into the initial prediction model for training.

[0122] Specifically, train the initial prediction model with the processed historical operating condition data to obtain a prediction model with a prediction accuracy meeting the threshold.

[0123] In a possible implementation, as Figure 8 shown, step S103 processing the historical operating condition data to generate a sample data set specifically includes the following steps:

[0124] Step S1031: Find the fields in the historical operating condition data where the monitoring data is null;

[0125] Step S1032: Fill the fields with null monitoring data to generate the first training sub-data;

[0126] Among them, the sample data set includes multiple first training sub-data;

[0127] Specifically, find the fields where the value of the monitoring data corresponding to each field in each historical operating condition data is null. Since the data reporting cycles of each monitoring item are different in actual operation, there will be cases where the monitoring values corresponding to some fields are null during data collection. In order to ensure that the training of the initial prediction model is more effective after inputting the training data into the initial prediction model, it is necessary to fill and complete the values of the monitoring data in the fields with null monitoring data.

[0128] Among them, the sample data set includes multiple first training sub-data. The first training sub-data includes both the first training sub-data generated after supplementing the null value fields and the historical operating condition data where there are no null values in all fields and no filling is required.

[0129] Sixty percent of the data in the sample dataset is put into the training dataset for training the initial prediction model, and the remaining forty percent of the data is put into the test dataset for verifying the prediction accuracy of the trained prediction model. When the prediction accuracy of the prediction model is greater than or equal to the threshold, the prediction model is successfully constructed. When the prediction accuracy of the prediction model is less than the threshold, the prediction model is retrained.

[0130] After step S1032, step S1033 is further included;

[0131] Step S1033: Sample the data in the sample dataset. Put sixty percent of the sampled data into the training dataset for training the initial prediction model, and put the remaining forty percent of the sampled data into the test dataset for verifying the prediction accuracy of the trained prediction model.

[0132] Specifically, by adding the data sampling step, the randomness of the data can be made stronger, and thus the accuracy of the prediction model trained with this data can be improved. The sampling method can be to sample the data at a certain sampling period. For example, if the sampling period is 60 seconds, then sample all the data in the sample dataset in step S1032 at a rate of sampling one data every 60 seconds. Or sample all the data in the sample dataset in step S1032 by other existing sampling methods, and use the data generated by multiple samplings as the data in the sample dataset in step S104.

[0133] In a possible implementation manner, Figure 9 The following shows a schematic flowchart of a method for identifying the steering of a vehicle mixing drum provided by another embodiment of the present application. As Figure 9 shown, step S1032 of filling the fields with null monitoring data to generate the first training sub-data specifically includes the following steps:

[0134] Step S10321: According to the time point of the historical working condition data corresponding to the field with null monitoring data, obtain a plurality of monitoring data generated within the first preset duration before the time point and within the second preset duration after the time point;

[0135] Step S10322: Calculate the average value of the plurality of monitoring data, and fill the average value into the field with null value to generate the first training sub-data.

[0136] Specifically, when filling in the fields with null monitoring data, it is achieved by obtaining the values of multiple monitoring data generated within the first preset duration before the time point and the second preset duration after the time point, and then calculating the average value of the values of the multiple monitoring data and filling the average value into the null values. Usually, the first preset duration and the second preset duration can be determined according to the time usage situation, and it is necessary to ensure that at least two sets of values of the monitoring data are obtained within the first preset duration and the second preset duration.

[0137] In a possible implementation manner, Figure 10 The figure shows a schematic flowchart of a method for identifying the steering of a vehicle mixing drum provided by another embodiment of the present application. As Figure 10 shown, before filling in the fields with null monitoring data in step S1032 to generate the first training sub-data, the data processing of the historical working condition data in step S103 further includes the following steps:

[0138] Step S10311: Search for the fields corresponding to multiple monitoring data in each historical working condition data;

[0139] Step S10312: Calculate the average value of the multiple monitoring data, and replace the multiple monitoring data with aligned monitoring data, where the aligned monitoring data is the average value.

[0140] Specifically, in the actual use process, the acquisition and reporting cycle of the sensor of a certain monitoring item may be a time unit smaller than seconds, such as milliseconds. Therefore, when obtaining historical working condition data in seconds, in a piece of historical working condition data, there may be a situation where there are multiple monitoring data in a certain field. At this time, it is necessary to convert the multiple monitoring data into a single monitoring data, that is, the aligned monitoring data, so that each field corresponds to a unique value of the monitoring data.

[0141] In a possible implementation manner, as Figure 11 shown, step S103 performs data processing on the historical working condition data to generate a sample data set, which specifically includes the following steps:

[0142] Step S1034: Search for the noise fields in the historical working condition data;

[0143] Step S1035: Remove the noise fields.

[0144] Specifically, when removing weakly correlated fields, the Pearson correlation coefficient of each field in the historical working condition data can be calculated first;

[0145] When the Pearson correlation coefficient is lower than the threshold, the field is removed.

[0146] When the Pearson correlation coefficient is lower than the threshold, it indicates that the correlation between the field and the prediction target is relatively small and can be directly excluded.

[0147] In a possible implementation, as Figure 12 shown, after generating the current steering data of the mixing drum according to the prediction result in step S14, the vehicle mixing drum steering recognition method further includes:

[0148] Step S15: Obtain first steering data, where the first steering data includes the steering data of the mixing drum obtained by a steering sensor;

[0149] Step S16: Compare the current steering data with the first steering data to generate a steering comparison result;

[0150] Step S17: When the steering comparison result indicates that the current steering data is consistent with the steering information represented by the first steering data, use the current steering data as the actual steering result of the mixing drum.

[0151] In addition, when the steering comparison result indicates that the current steering data is inconsistent with the steering information represented by the first steering data, an alarm message is issued.

[0152] By adding the step of comparing the current steering data obtained through calculation by the prediction model with the first steering data obtained by the actual steering sensor, the accuracy of the current steering data calculated by the prediction model can be further improved, and the vehicle use safety can be further enhanced.

[0153] Exemplary device

[0154] As a second aspect of the present application, as Figure 13 shown, the present application provides a vehicle mixing drum steering recognition device for executing the above-mentioned vehicle mixing drum steering recognition method, which includes:

[0155] A model construction module 10 that constructs a prediction model according to vehicle historical working condition data and mixing drum steering data, where the vehicle historical working condition data includes one or more of engine speed, upper-mounted motor torque, upper-mounted motor current, vehicle voltage, and mixing drum speed;

[0156] A data acquisition module 11 for acquiring the current working condition data of the vehicle;

[0157] A data input module 12 for inputting the current working condition data into the prediction model;

[0158] An identification module 13 for obtaining a prediction result output by the prediction model, where the prediction result includes the current rotation state of the mixing drum of the vehicle, and the current rotation state of the mixing drum corresponds to the current working condition data in time; and generating the current steering data of the mixing drum according to the prediction result.

[0159] Specifically, the identification module 13 includes:

[0160] A steering determination parameter assignment module, configured to assign a steering determination parameter to the sum of a preset value and a first value when the prediction result indicates that the current rotation state of the mixing drum is reverse. The first value is the value assigned to the previous steering determination parameter of the mixing drum, and the value assigned to the previous steering determination parameter of the mixing drum corresponds to the previous working condition data of the mixing drum. Wherein, the previous working condition data and the current working condition data are arranged in sequence in terms of time.

[0161] A steering determination module, configured to determine that the current steering data of the mixing drum is reverse when the steering determination parameter is greater than or equal to a threshold value.

[0162] Exemplary device

[0163] As a third aspect of the present application, the present application provides an engineering vehicle, including:

[0164] A mixing drum and the vehicle mixing drum steering recognition device in the above embodiments.

[0165] Exemplary Electronic Device

[0166] Next, with reference to Figure 14 to describe an electronic device according to an embodiment of the present application. Figure 14 The following shows a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0167] As Figure 14 shown, the electronic device 600 includes one or more processors 601 and a memory 602.

[0168] The processor 601 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or information execution capabilities, and may control other components in the electronic device 600 to perform desired functions.

[0169] The memory 601 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program information may be stored on the computer-readable storage medium, and the processor 601 may run the program information to implement the vehicle mixing drum steering recognition method of the various embodiments of the present application above or other desired functions.

[0170] In one example, the electronic device 600 may further include: an input device 603 and an output device 604, and these components are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0171] The input device 603 may include, for example, a keyboard, a mouse, and so on.

[0172] The output device 604 may output various information to the outside. The output device 604 may include, for example, a display, a communication network, and remote output devices connected thereto, and so on.

[0173] Of course, for simplicity, Figure 14 only some of the components related to the present application in the electronic device 600 are shown, and components such as a bus, an input / output interface, and so on are omitted. In addition, according to specific application scenarios, the electronic device 600 may further include any other appropriate components.

[0174] In addition to the above methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program information. When the computer program information is run by a processor, the processor is caused to execute the steps in the vehicle mixing drum steering recognition method according to various embodiments of the present application described in this specification.

[0175] The computer program product may be written in any combination of one or more programming languages for programming code to perform the operations of the embodiments of the present application. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The programming code may be executed entirely on the user computing device, partially on the user device, executed 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.

[0176] In addition, an embodiment of the present application may also be a computer-readable storage medium, on which computer program information is stored. When the computer program information is run by a processor, the processor is caused to execute the steps in the vehicle mixing drum steering recognition method according to various embodiments of the present application described in this specification.

[0177] A computer-readable storage medium may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having 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.

[0178] The basic principles of the present application have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are only examples and not limitations. It cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of the present application. In addition, the above-disclosed specific details are only for illustrative and easy-to-understand purposes, rather than limitations. These details do not limit the present application to necessarily adopt the above specific details for implementation.

[0179] The block diagrams of the devices, apparatuses, equipment, and systems involved in the present application are only illustrative examples and do not intend to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open-ended words, meaning "including but not limited to", and can be interchanged with each other. The word "or" and "and" passed here refer to the word "and / or", and can be interchanged with each other, unless the context clearly indicates otherwise. The word "such as" passed here refers to the phrase "such as but not limited to", and can be interchanged with each other.

[0180] It should also be noted that in the devices, equipment, and methods of the present application, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of the present application.

[0181] The above description of the disclosed aspects enables any person skilled in the art to make or practice through the present application. Various modifications to these aspects are very obvious to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the broadest scope consistent with the principles and novel features claimed herein.

[0182] The above are only the preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent substitutions, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for identifying the steering of a vehicle mixing drum, characterized in that, Including: Construct a prediction model based on vehicle historical operating condition data and mixer drum rotation data, wherein the operating condition data includes one or more of engine speed, upper-mounted motor torque, upper-mounted motor current, vehicle voltage, and mixer drum speed; Obtain the current operating condition data of the vehicle; Input the current operating condition data into the prediction model; Obtain the prediction result output by the prediction model, the prediction result includes the current rotation state of the mixer drum of the vehicle, and the current rotation state of the mixer drum corresponds to the current operating condition data in time; and Generate the current rotation data of the mixer drum according to the prediction result; When the prediction result is that the current rotation state of the mixer drum is reverse, assign a steering determination parameter to the sum of a preset value and a first value, the first value is the value assigned to the previous steering determination parameter of the mixer drum, and the value assigned to the previous steering determination parameter of the mixer drum corresponds to the previous operating condition data of the mixer drum, wherein the previous operating condition data and the current operating condition data are arranged in time sequence; When the prediction result is that the current rotation state of the mixer drum is forward, the current rotation data of the mixer drum is forward rotation.

2. The vehicle mixing drum steering recognition method according to claim 1, wherein, Generating the current rotation data of the mixer drum of the vehicle according to the prediction result includes: When the steering determination parameter is greater than or equal to the threshold, the current rotation data of the mixer drum is reverse rotation.

3. The vehicle mixing drum steering recognition method according to claim 2, wherein, Generating the current rotation data of the mixer drum of the vehicle according to the prediction result includes: When the steering determination parameter is less than the threshold, the current rotation data of the mixer drum is forward rotation.

4. The vehicle mixing drum steering recognition method according to claim 1, characterized in that, The constructing of the prediction model includes: Construct an initial prediction model; Obtain multiple groups of historical operating condition data and the mixer drum rotation data at the corresponding moments of the historical operating condition data, each group of the historical operating condition data includes multiple fields, and each field corresponds to monitoring data; Perform data processing on the historical operating condition data and the mixer drum rotation data to generate a sample data set; and Input the data in the sample data set into the initial prediction model for training.

5. The vehicle mixing drum steering recognition method according to claim 4, characterized in that, Performing data processing on the historical operating condition data and the mixer drum rotation data to generate a sample data set includes: Find the fields in the historical operating condition data where the monitoring data is null; Fill the fields where the monitoring data is null to generate the first training sub-data; Wherein, the sample data set includes multiple first training sub-data.

6. The vehicle mixing drum steering recognition method according to claim 4, characterized in that, Performing data processing on the historical operating condition data and the mixer drum rotation data to generate a sample data set includes: Find the noise fields in the historical operating condition data; Remove the noise fields.

7. The vehicle mixing drum steering recognition method according to claim 1, wherein, After obtaining the current operating condition data of the vehicle, the vehicle mixer drum rotation recognition method further includes: Find the fields in the current operating condition data where the monitoring data is null; Fill the fields where the monitoring data is null.

8. The vehicle mixing drum steering recognition method according to claim 1, characterized in that, After generating the current rotation data of the mixer drum according to the prediction result, the vehicle mixer drum rotation recognition method further includes: Obtain the first rotation data, the first rotation data includes the rotation data of the mixer drum obtained by a rotation sensor; Compare the current steering data with the first steering data to generate a steering comparison result; When the steering comparison result indicates that the steering information represented by the current steering data is consistent with that represented by the first steering data, use the current steering data as the actual steering result of the mixing drum.

9. A vehicle mixing drum steering recognition device, characterized in that, Comprising: A model construction module for constructing a prediction model based on vehicle historical operating condition data and mixing drum steering data, wherein the operating condition data includes one or more of engine speed, torque of the upper-mounted motor, current of the upper-mounted motor, vehicle voltage, and mixing drum speed; A data acquisition module for acquiring the current operating condition data of the vehicle; A data input module for inputting the operating condition data into the prediction model; An identification module for obtaining the prediction result output by the prediction model, the prediction result including the current rotation state of the mixing drum of the vehicle, the current rotation state of the mixing drum corresponding to the current operating condition data in terms of time; and generating the current steering data of the mixing drum according to the prediction result; when the prediction result is that the current rotation state of the mixing drum is reverse rotation, assign a steering determination parameter a value equal to the sum of a preset value and a first value, the first value being the value assigned to the previous steering determination parameter of the mixing drum, the value assigned to the previous steering determination parameter of the mixing drum corresponding to the previous operating condition data of the mixing drum, wherein the previous operating condition data and the current operating condition data are arranged in sequence in terms of time; when the prediction result is that the current rotation state of the mixing drum is forward rotation, the current steering data of the mixing drum is forward rotation.

10. An engineering vehicle, characterized in that, Comprising: A mixing drum; And The vehicle mixing drum steering identification device as claimed in claim 9.

Images