Pump truck concrete pipe service life prediction method, electronic equipment and machine readable storage medium

Abstract

The invention discloses a pump truck concrete pipe service life prediction method, electronic equipment and a machine readable storage medium, and relates to the field of engineering machinery, the prediction method comprises the following steps: carrying out vectorization processing on a concrete pipe brand, and obtaining first feature data; performing feature extraction and vectorization processing on the concrete pipe use time and the boom angle proportion of the pump truck to obtain vectorized second feature data; performing feature extraction and discretization processing on the pumping pressure and the boom inclination angle of the pump truck to obtain discretized third feature data; performing feature extraction on the first feature data, the vectorized second feature data and the discretized third feature data to obtain concrete pipe service life feature data; and carrying out classification processing on the concrete pipe service life characteristic number by utilizing DNN characteristic classification so as to determine the residual service life interval of the concrete pipe. According to the invention, interference caused by excessive continuous feature data can be prevented, and the prediction accuracy is improved.

Description

Technical Field

[0001] The present application relates to the technical field of engineering machinery, and specifically to a method for predicting the life of a concrete pipe of a pump truck, a system for predicting the life of a concrete pipe of a pump truck, an electronic device, and a machine-readable storage medium. Background Art

[0002] The existing identification of the life of concrete delivery pipes on pump trucks is carried out through regression analysis to determine the relationship between selected features and concrete delivery pipes. This continuous prediction method is difficult to converge and obtain good results during model training due to its high complexity. At the same time, since the data cannot cover all working conditions, it will also affect the training results, resulting in poor actual effect of the model in generalization ability.

[0003] In addition, the existing concrete pipe life prediction is to extract features and then build a single model to predict the life. Due to the complexity of the concrete pipe life, it is difficult for a single model to correctly fit the data, resulting in low prediction accuracy. Therefore, how to prevent interference caused by excessive continuous feature data and how to improve the accuracy of life prediction for concrete pump truck delivery pipes are important issues of concern to people in this field. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method for predicting the life of a concrete pipe of a pump truck, a system for predicting the life of a concrete pipe of a pump truck, an electronic device and a machine-readable storage medium, so as to partially or completely solve the problems in the prior art of interference caused by excessive continuous feature data and low accuracy of life prediction.

[0005] In order to achieve the above-mentioned objectives, the first aspect of the present application provides a method for predicting the life of a concrete pipe of a pump truck.

[0006] In an embodiment of the present application, the prediction method includes: vectorizing the concrete pipe brand to obtain first feature data; extracting features of the concrete pipe usage time and the boom angle ratio of the pump truck to obtain second feature data; vectorizing the second feature data to obtain vectorized second feature data; extracting features of the pumping pressure and the boom inclination angle of the pump truck to obtain third feature data; discretizing the third feature data to obtain discretized third feature data; extracting features from the first feature data, the vectorized second feature data and the discretized third feature data to obtain concrete pipe life feature data; and classifying the concrete pipe life feature number using DNN feature classification to determine the remaining life interval of the concrete pipe.

[0007] Optionally, the use of DNN feature classification to classify the concrete pipe life characteristic numbers to determine the remaining life interval of the concrete pipe includes: using DNN feature classification to classify the concrete pipe life characteristic numbers to obtain the probability of the concrete pipe in multiple preset remaining life intervals; determining the preset remaining life interval with the largest value corresponding to the probability of the concrete pipe in multiple preset remaining life intervals as the remaining life interval of the concrete pipe.

[0008] Optionally, the vectorizing the concrete pipe brand to obtain the first feature data includes: one-hot encoding the concrete pipe brand to obtain a one-dimensional vector of the concrete pipe brand; converting the one-dimensional vector of the concrete pipe brand into a multi-dimensional vector to obtain the first feature data.

[0009] Optionally, the feature extraction of the concrete pipe usage time and the boom angle ratio of the pump truck to obtain the second feature data includes: normalizing the concrete pipe usage time and the boom angle ratio of the pump truck to obtain corresponding normalized values; and feature extraction of the normalized values ​​to obtain the second feature data.

[0010] Optionally, the third feature data is discretized to obtain the discretized third feature data, including: using an LSTM time series model to process the third feature data to obtain third feature data with time series characteristics; discretizing the third feature data with time series characteristics to obtain discretized third feature data.

[0011] Optionally, before executing the step of performing feature extraction on the pumping pressure and the boom angle of the pump truck to obtain the third feature data, the prediction method also includes: vectorizing the pumping pressure and the boom angle of the pump truck to obtain the vectorized pumping pressure and boom angle data of the pump truck; performing feature extraction on the vectorized pumping pressure and boom angle data of the pump truck to obtain the third feature data.

[0012] The second aspect of the present application provides a prediction system for the life of concrete pipes of pump trucks, including: a first acquisition module, used to vectorize the brand of concrete pipes to obtain first feature data; a second acquisition module, used to extract features of the use time of concrete pipes and the angle ratio of the boom of the pump truck to obtain second feature data; a third acquisition module, used to vectorize the second feature data to obtain vectorized second feature data; a fourth acquisition module, used to extract features of pumping pressure and the inclination angle of the boom of the pump truck to obtain third feature data; a fifth acquisition module, used to discretize the third feature data to obtain discretized third feature data; a sixth acquisition module, used to extract features from the first feature data, the vectorized second feature data and the discretized third feature data to obtain concrete pipe life feature data; a determination module, used to classify the concrete pipe life feature number using DNN feature classification to determine the remaining life interval of the concrete pipe.

[0013] Furthermore, the determination module is used to classify the concrete pipe life characteristic numbers using DNN feature classification to determine the remaining life interval of the concrete pipe, including: classifying the concrete pipe life characteristic numbers using DNN feature classification to obtain the probability of the concrete pipe in multiple preset remaining life intervals; determining the preset remaining life interval with the largest value corresponding to the probability of the concrete pipe in multiple preset remaining life intervals as the remaining life interval of the concrete pipe.

[0014] The third aspect of the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method for predicting the life of a concrete pipe of a pump truck as described above.

[0015] A fourth aspect of the present application provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the method for predicting the life of a concrete pipe of a pump truck.

[0016] Through the above technical scheme, the embodiment of the present invention extracts and discretizes the features of concrete pipe brand, concrete pipe usage time and boom angle ratio to remove redundant information to the greatest extent and retain the main information; the pumping pressure and the boom inclination angle of the pump truck are first feature extracted, then time series feature processed and finally discretized to extract the effective information of the pumping pressure and boom inclination angle data, thereby preventing interference caused by excessive continuous feature data.

[0017] In addition, the present invention extracts features from multiple aspects such as concrete pipe brand, concrete pipe usage time, boom angle ratio of pump truck, pumping pressure and boom inclination angle of pump truck, extracts concrete pipe life characteristic data related to the concrete pipe life, and classifies the extracted concrete pipe life characteristic data to finally predict the concrete pipe life range, which can better explain whether the deviation value is consistent with the true value, thereby improving the accuracy of predicting the concrete pipe life.

[0018] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0020] Figure 1 It is a flow chart of a method for predicting the life of a concrete pipe of a pump truck according to an embodiment of the present application;

[0021] Figure 2 It is an overall flow chart of a method for predicting the life of a concrete pipe of a pump truck provided by an embodiment of the present invention;

[0022] Figure 3 It is a schematic diagram of the structure of a system for predicting the life of a concrete pipe of a pump truck provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0024] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0025] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0026] Figure 1 The following is a schematic diagram of a method for predicting the life of a concrete pipe of a pump truck according to an embodiment of the present application. Figure 1 As shown, an embodiment of the present application provides a method for predicting the life of a concrete pipe of a pump truck, and the method may include the following steps.

[0027] Step 101: perform vector processing on the concrete pipe brand to obtain first characteristic data.

[0028] Furthermore, the vectorization processing of the concrete pipe brand to obtain the first characteristic data includes steps 1011-1012.

[0029] Step 1011: One-hot encode the concrete pipe brand to obtain a one-dimensional vector of the concrete pipe brand.

[0030] In the embodiment of the present application, one-hot encoding is performed on the concrete pipe brand of the concrete pump truck. The purpose of encoding is to convert the feature from text to a one-dimensional vector. For example, the three brands "Zhonglian 1", "Zhonglian 2", and "Zhonglian 3" have the following conversion results: [1, 0, 0], [0, 1, 0], [0, 0, 1].

[0031] Step 1012: Convert the one-dimensional vector of the concrete pipe brand into a multi-dimensional vector to obtain first characteristic data.

[0032] In the embodiment of the present application, the one-dimensional vector of the concrete pipe brand is converted into a multi-dimensional vector (specifically, the existing technical means can be used, and the embodiment of the present invention does not make specific restrictions) as the subsequent model input. The purpose of the conversion is to align with the dimensions of other data. Vectors with different dimensions cannot be added or subtracted. Among them, the first feature data, that is, the data after the one-dimensional vector in step 1011 is converted into a multi-dimensional vector.

[0033] Step 102: extract features of the concrete pipe usage time and the boom angle ratio of the pump truck to obtain second feature data.

[0034] Furthermore, the feature extraction of the concrete pipe use time and the boom angle ratio of the pump truck to obtain the second feature data includes the following steps 1021-1022.

[0035] Step 1021, normalize the use time of the concrete pipe and the boom angle ratio of the pump truck to obtain corresponding normalized values.

[0036] In the embodiment of the present application, the proportion of the boom angle of the pump truck within the concrete pipe use time and working condition range is normalized. The purpose of normalization is to disperse the value into the range of 0 to 1 and determine the upper limit of the value. For example: the concrete pipe use time (unit: hours) is 0.5, 10, 500, 200, then the processing method is: minimum value = (0.5-0.5) / (500-0.5), maximum value = (500-0.5) / (500-0.5).

[0037] Step 1022: Perform feature extraction on the normalized value to obtain second feature data.

[0038] In the embodiment of the present application, the normalized value of the boom angle ratio of the pump truck within the concrete pipe use time and working condition range is subjected to PCA principal component analysis to extract features, and corresponding second feature data is obtained.

[0039] Step 103: perform vectorization processing on the second feature data to obtain vectorized second feature data.

[0040] In the embodiment of the present application, the proportion of the boom angle within the concrete pipe service time and working condition range is extracted using PCA to obtain the second feature data. The second feature data is then vectorized to obtain the vectorized second feature data. The vectorization is to unify the dimension of the vector for subsequent vector operations.

[0041] Step 104: extract the features of the pumping pressure and the boom inclination angle of the pump truck to obtain third feature data.

[0042] Before executing the step of extracting the features of the pumping pressure and the boom inclination angle of the pump truck to obtain the third feature data, the prediction method further includes steps 1041-1042.

[0043] Step 1041: vectorize the pumping pressure and the boom inclination angle of the pump truck to obtain vectorized pumping pressure and boom inclination angle data of the pump truck.

[0044] In the embodiment of the present application, the data of the pumping pressure and the boom inclination angle are vectorized. The purpose of vectorization is to convert the data dimension into the data dimension required by the model input. At the same time, the data after vectorization is more convenient for the model to extract features. The pumping pressure and the boom inclination angle of the pump truck in the embodiment of the present invention are both time series feature continuous values.

[0045] Step 1042: extract features from the vectorized pumping pressure and boom inclination angle data of the pump truck to obtain third feature data.

[0046] In the embodiment of the present application, Encoder1 is used to extract features from the quantized data of the pumping pressure and the boom inclination angle to obtain third feature data. Encoder1 is an encoder based on the Transformer architecture.

[0047] Step 105: discretize the third characteristic data to obtain discretized third characteristic data.

[0048] Furthermore, the third characteristic data is discretized to obtain the discretized third characteristic data, including the following steps 1051-1052.

[0049] Step 1051: Use the LSTM time series model to process the third feature data to obtain third feature data with time series characteristics.

[0050] In the embodiment of the present application, the LSTM time series model is used to process the third feature data output after Encoder1. The purpose of this step is to extract the pumping pressure and boom inclination angle features (ie, the third feature data) with time series characteristics.

[0051] Step 1052: discretize the third characteristic data having time series characteristics to obtain discretized third characteristic data.

[0052] In an embodiment of the present application, the time series characteristics of the pumping pressure and the boom inclination angle extracted by LSTM (i.e., the third feature data with time series characteristics) are discretized. The discretization process is to separate the continuous time series characteristics into different intervals for use as input data for subsequent models.

[0053] The present invention mainly utilizes One-hot encoding to vectorize the brand of concrete pipes, uses a normalization method to process the proportion of boom angles within the service time and working condition range of the conveying pipes, extracts features through the PCA principal component analysis method, uses the encoder of the Transformer result to extract continuous features and fusion features, and uses the DNN network structure to classify the life of concrete pipes.

[0054] However, in practice, methods such as CNN and RNN can also be used to extract features, and networks such as CNN can be used for classification. After building the same structure according to the present invention, similar results to those of the present invention can be achieved.

[0055] Step 106: extract features from the first feature data, the vectorized second feature data, and the discretized third feature data to obtain concrete pipe life feature data.

[0056] In an embodiment of the present application, the first feature data, the vectorized second feature data and the discretized third feature data obtained in the above steps are input into Encoder2 for feature extraction. The purpose of Encoder2 is to combine different data and then comprehensively extract the concrete pipe life features to obtain concrete pipe life feature data.

[0057] Step 107: classify the concrete pipe life feature number using DNN feature classification to determine the remaining life interval of the concrete pipe. Step 107 also includes the following steps 1071-1072.

[0058] Compared with the existing method of directly using continuous features, the present invention first uses a time series model to extract features from the pumping pressure and boom inclination data and then introduces the extracted features as input into the classification model. This method can effectively extract valid information from the continuous data while filtering out invalid information. The existing method generally directly predicts the life of the concrete pipe, which is greatly affected by the data and difficult to train. The method proposed in this patent to determine the life range of the concrete pipe through a classification method can more effectively utilize the data and ensure the accuracy of the results.

[0059] Step 1071: classify the concrete pipe life feature number using DNN feature classification to obtain the probability of the concrete pipe being in multiple preset remaining life intervals.

[0060] In the embodiment of the present application, for example, multiple preset remaining life intervals are: life 0-20%, life 20%-40%, life 40%-60%, life 60%-80%, life 80%-100%. The life interval represents the remaining life interval of the concrete pipe. In the embodiment of the present invention, the preset remaining life interval is set to 5 intervals, and the setting of the interval can be increased or decreased accordingly according to actual needs. The more refined the preset remaining life interval setting (that is, the more preset remaining life intervals), the more accurate the prediction result. For example, the preset remaining life interval can be set to: life 0-10%, life 20%-30%, life 30%-40%... life 90%-100%, a total of 10 preset remaining life intervals. The above-mentioned division of the preset remaining life intervals of the present invention is exemplary, and the present invention does not make specific limitations. The methods of similar division based on the embodiments of the present invention belong to the protection scope of the present invention.

[0061] The DNN feature classification is used to classify the characteristic numbers of the concrete pipe life, and the softmax activation function is used to calculate the probability of the concrete pipe in multiple preset remaining life intervals. For example, the probabilities of the concrete pipe in a life of 0-20%, a life of 20%-40%, a life of 40%-60%, a life of 60%-80%, and a life of 80%-100% are 0.1, 0.2, 0.4, 0.05, and 0.25, respectively.

[0062] Step 1072: Determine the preset remaining life interval with the largest value corresponding to the probability of the concrete pipe in multiple preset remaining life intervals as the remaining life interval of the concrete pipe.

[0063] In the embodiment of the present application, the output of the DNN model is a probability distribution, which indicates the probability that the input data belongs to each category. In order to obtain a specific category prediction, it is necessary to find the category with the highest probability in this probability distribution, which is usually achieved by taking the index of the maximum value in the output vector.

[0064] As described in the above steps, the probabilities corresponding to the preset remaining life intervals are obtained, wherein the maximum probability value corresponding to a life of 40%-60% is 0.4, and therefore the life of 40%-60% is determined as the remaining life interval of the concrete pipe. According to the embodiment of the present invention, the remaining life interval of the concrete pipe can be determined, the predicted life percentage interval of the concrete pipe can be determined, and this information can also be used for further analysis, reporting or decision making. It should be noted that the concrete pipe in the embodiment of the present invention refers to the concrete pipe to be predicted. Figure 2 It is an overall flow chart of a method for predicting the life of a concrete pipe of a pump truck provided by an embodiment of the present invention.

[0065] Compared with the existing process, the improvement produced by the present invention is that: by extracting the continuous characteristics of pumping pressure and boom inclination angle first, then processing the time series characteristics and finally discretizing them, the effective information of the data of pumping pressure and boom inclination angle is extracted, thereby preventing the interference caused by too much continuous feature data; by extracting and discretizing the characteristics of concrete pipe brand, concrete pipe usage time and boom angle ratio, redundant information is removed to the greatest extent and the main information is retained, and finally the classification method is used to take the above data as input to obtain the interval range of concrete pipe life.

[0066] Through the above technical scheme, the embodiment of the present invention extracts and discretizes the features of concrete pipe brand, concrete pipe usage time and boom angle ratio to remove redundant information to the greatest extent and retain the main information; the pumping pressure and the boom inclination angle of the pump truck are first feature extracted, then time series feature processed and finally discretized to extract the effective information of the pumping pressure and boom inclination angle data, thereby preventing interference caused by excessive continuous feature data.

[0067] In addition, the present invention extracts features from multiple aspects such as concrete pipe brand, concrete pipe usage time, boom angle ratio of pump truck, pumping pressure and boom inclination angle of pump truck, extracts concrete pipe life characteristic data related to the concrete pipe life, and classifies the extracted concrete pipe life characteristic data to finally predict the concrete pipe life range, which can better explain whether the deviation value is consistent with the true value, thereby improving the accuracy of predicting the concrete pipe life.

[0068] Figure 3 The following schematically shows a structural diagram of a prediction system for the life of a concrete pipe of a pump truck according to an embodiment of the present application. Figure 3 As shown, in an embodiment of the present application, the prediction system 30 includes: a first acquisition module 301, which is used to vectorize the concrete pipe brand and obtain the first feature data; a second acquisition module 302, which is used to extract the features of the concrete pipe usage time and the boom angle ratio of the pump truck and obtain the second feature data; a third acquisition module 303, which is used to vectorize the second feature data and obtain the vectorized second feature data; a fourth acquisition module 304, which is used to extract the features of the pumping pressure and the boom inclination angle of the pump truck and obtain the third feature data; a fifth acquisition module 305, which is used to discretize the third feature data and obtain the discretized third feature data; a sixth acquisition module 306, which is used to extract the features of the first feature data, the vectorized second feature data and the discretized third feature data to obtain the concrete pipe life feature data; a determination module 307, which is used to classify the concrete pipe life feature number using DNN feature classification to determine the remaining life interval of the concrete pipe.

[0069] Through the above technical scheme, the embodiment of the present invention extracts and discretizes the features of concrete pipe brand, concrete pipe usage time and boom angle ratio to remove redundant information to the greatest extent and retain the main information; the pumping pressure and the boom inclination angle of the pump truck are first feature extracted, then time series feature processed and finally discretized to extract the effective information of the pumping pressure and boom inclination angle data, thereby preventing interference caused by excessive continuous feature data.

[0070] In addition, the present invention extracts features from multiple aspects such as concrete pipe brand, concrete pipe usage time, boom angle ratio of pump truck, pumping pressure and boom inclination angle of pump truck, extracts concrete pipe life characteristic data related to the concrete pipe life, and classifies the extracted concrete pipe life characteristic data to finally predict the concrete pipe life range, which can better explain whether the deviation value is consistent with the true value, thereby improving the accuracy of predicting the concrete pipe life.

[0071] Furthermore, the determination module is used to classify the concrete pipe life characteristic numbers using DNN feature classification to determine the remaining life interval of the concrete pipe, including: classifying the concrete pipe life characteristic numbers using DNN feature classification to obtain the probability of the concrete pipe in multiple preset remaining life intervals; determining the preset remaining life interval with the largest value corresponding to the probability of the concrete pipe in multiple preset remaining life intervals as the remaining life interval of the concrete pipe.

[0072] Another embodiment of the present invention also provides an electronic device, including: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method for predicting the life of a concrete pipe of a pump truck as described above.

[0073] The implementation principle and effect of the system for predicting the life of a concrete pipe of a pump truck in the embodiment of the present invention are similar to the above-mentioned method for predicting the life of a concrete pipe of a pump truck, and will not be described in detail herein.

[0074] The embodiment of the present application also provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute the above-mentioned method for predicting the life of a concrete pipe of a pump truck.

[0075] The implementation principle and effect of the system for predicting the life of a concrete pipe of a pump truck in the embodiment of the present invention are similar to the above-mentioned method for predicting the life of a concrete pipe of a pump truck, and will not be described in detail herein.

[0076] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0077] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0078] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0079] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0080] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0081] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0082] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0083] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0084] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for predicting the life of a concrete pipe of a pump truck, characterized in that: The prediction method comprises: Perform vector processing on the concrete pipe brand to obtain the first characteristic data; Extract features of the concrete pipe usage time and the boom angle ratio of the pump truck to obtain second feature data; Performing vectorization processing on the second feature data to obtain vectorized second feature data; Extract the pumping pressure and the boom inclination angle of the pump truck to obtain the third feature data; Performing discretization processing on the third characteristic data to obtain discretized third characteristic data; Perform feature extraction on the first feature data, the vectorized second feature data and the discretized third feature data to obtain concrete pipe life feature data; The DNN feature classification is used to classify the concrete pipe life feature number to determine the remaining life interval of the concrete pipe.

2. The prediction method according to claim 1, characterized in that: The method of using DNN feature classification to classify the concrete pipe life feature number to determine the remaining life interval of the concrete pipe includes: Using DNN feature classification to classify the concrete pipe life feature number, and obtain the probability of the concrete pipe being in multiple preset remaining life intervals; The preset remaining life interval with the largest value corresponding to the probability of the concrete pipe in the plurality of preset remaining life intervals is determined as the remaining life interval of the concrete pipe.

3. The prediction method according to claim 1, characterized in that: The vectorization processing of the concrete pipe brand to obtain the first characteristic data includes: One-hot encoding is performed on the concrete pipe brand to obtain a one-dimensional vector of the concrete pipe brand; The one-dimensional vector of the concrete pipe brand is converted into a multi-dimensional vector to obtain first characteristic data.

4. The prediction method according to claim 1, characterized in that: The feature extraction of the concrete pipe use time and the boom angle ratio of the pump truck to obtain the second feature data includes: The concrete pipe use time and the boom angle ratio of the pump truck are normalized to obtain corresponding normalized values; Perform feature extraction on the normalized value to obtain second feature data.

5. The prediction method according to claim 1, characterized in that: Discretizing the third characteristic data to obtain the discretized third characteristic data includes: The third feature data is processed using the LSTM time series model to obtain the third feature data with time series characteristics; Discretization processing is performed on the third characteristic data having time series characteristics to obtain discretized third characteristic data.

6. The prediction method according to claim 1, characterized in that: Before performing the step of extracting the features of the pumping pressure and the boom inclination angle of the pump truck to obtain the third feature data, the prediction method further includes: Vectorizing the pumping pressure and the boom inclination angle of the pump truck to obtain vectorized pumping pressure and boom inclination angle data of the pump truck; Feature extraction is performed on the vectorized pumping pressure and boom inclination angle data of the pump truck to obtain third feature data.

7. A prediction system for the life of a concrete pipe of a pump truck, characterized in that: include: A first acquisition module is used to perform vectorization processing on the concrete pipe brand to obtain first characteristic data; The second acquisition module is used to extract features of the concrete pipe use time and the boom angle ratio of the pump truck to obtain second feature data; A third acquisition module, used for performing vectorization processing on the second feature data to obtain vectorized second feature data; The fourth acquisition module is used to extract the characteristics of the pumping pressure and the boom inclination angle of the pump truck to obtain the third characteristic data; A fifth acquisition module, used for discretizing the third characteristic data to obtain discretized third characteristic data; A sixth acquisition module, used for performing feature extraction on the first feature data, the vectorized second feature data and the discretized third feature data to obtain concrete pipe life feature data; The determination module is used to classify the concrete pipe life feature number using DNN feature classification to determine the remaining life interval of the concrete pipe.

8. The prediction system according to claim 7, characterized in that The determination module is used to classify the concrete pipe life feature number using DNN feature classification to determine the remaining life interval of the concrete pipe, including: Using DNN feature classification to classify the concrete pipe life feature number, and obtain the probability of the concrete pipe being in multiple preset remaining life intervals; The preset remaining life interval with the largest value corresponding to the probability of the concrete pipe in the plurality of preset remaining life intervals is determined as the remaining life interval of the concrete pipe.

9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method for predicting the life of a concrete pipe of a pump truck as described in any one of claims 1-6.

10. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions for enabling the machine to execute the method for predicting the life of a concrete pipe of a pump truck according to any one of claims 1-6.

Images