A method and system for predicting energy consumption of an electric wheel self-unloading vehicle based on historical working conditions

Abstract

The application relates to the technical field of energy management, and discloses a kind of electric wheel dump truck energy consumption prediction method and system based on historical working condition, the method comprises: the working condition characteristic point of original operating parameter flow is serialized and arranged, and working condition characteristic sequence is obtained;Working condition characteristic sequence is matched with historical working condition characteristic sequence in historical working condition characteristic library in time sequence, and reference working condition characteristic sequence is obtained;Speed value is analyzed point by point deviation, and according to the deviation accumulation amount obtained by analysis, the historical energy consumption record value of historical working condition characteristic library is weightedly corrected, and actual energy consumption reference value is obtained;The front path is divided into continuous front road section fragments, and slope label is obtained;Historical energy consumption record value is indexed jointly, and basic energy consumption value is obtained;The total amount of predicted energy consumption is obtained by scaling the basic energy consumption value;The application can improve the efficiency of electric wheel dump truck energy consumption prediction.

Description

Technical Field

[0001] This invention relates to the field of energy management technology, and in particular to a method and system for predicting the energy consumption of electric wheel dump trucks based on historical operating conditions. Background Technology

[0002] Energy consumption prediction for electric wheel dump trucks largely relies on static calculations using fixed operating parameters, failing to analyze the dynamic characteristics of actual vehicle operation. This makes it impossible to accurately capture real-time changes in parameters such as vehicle speed and positioning during operation, resulting in significant discrepancies between the predicted energy consumption data and actual operating conditions, and failing to reflect the vehicle's true operating status. Existing technologies lack a comprehensive historical operating condition feature database and precise time-series matching between current and historical operating conditions. They rely solely on simple historical energy consumption records for reference, lacking systematic comparison and analysis of operating condition sequences, leading to a lack of specificity and effectiveness in the reference data for energy consumption prediction.

[0003] Existing energy consumption prediction methods for electric wheel dump trucks do not consider the impact of sudden slope changes on energy consumption, nor do they combine this with vehicle load capacity for joint indexing. Furthermore, the methods for dividing the road segmentation ahead lack scientific basis for slope characteristics, making it impossible to accurately retrieve and adapt historical energy consumption data based on actual road slope and load conditions. Simultaneously, existing technologies only analyze vehicle speed deviations at a single node level, failing to perform cumulative analysis of time-series speed deviations and use this data to weight and correct historical energy consumption records. The determination of energy consumption benchmark values ​​lacks a dynamic correction mechanism, ultimately resulting in low accuracy in energy consumption predictions and failing to meet the energy consumption control and scheduling needs of actual electric wheel dump truck operations. Summary of the Invention

[0004] This invention provides a method and system for predicting the energy consumption of electric wheel dump trucks based on historical operating conditions, in order to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a method for predicting the energy consumption of electric wheel dump trucks based on historical operating conditions, comprising:

[0006] Pt.1. Based on the running time sequence of the electric wheel dump truck, the working condition feature points of the original running parameter stream in the electric wheel dump truck are serialized and arranged to obtain the working condition feature sequence of the electric wheel dump truck.

[0007] Pt.2. Perform time-series normalization matching between the operating condition feature sequence and the historical operating condition feature sequence in the historical operating condition feature library of the electric wheel dump truck to obtain the reference operating condition feature sequence of the electric wheel dump truck.

[0008] Pt.3. Perform point-by-point deviation analysis on the vehicle speed values ​​at corresponding time positions in the operating condition feature sequence and the reference operating condition feature sequence, and perform weighted correction on the historical energy consumption record values ​​of the historical operating condition feature library based on the accumulated deviation obtained from the analysis, so as to obtain the actual energy consumption benchmark value of the electric wheel dump truck.

[0009] Pt.4. Based on the abrupt change points of the slope value in the preset slope map and combined with the actual energy consumption benchmark value, the forward path of the electric wheel dump truck is divided into continuous forward road segment segments to obtain the slope label of the electric wheel dump truck.

[0010] Pt.5. Based on the slope label and the load mass signal of the electric wheel dump truck, the historical energy consumption record value is jointly indexed to obtain the basic energy consumption value of the electric wheel dump truck.

[0011] Pt.6. Based on the actual energy consumption benchmark value, the basic energy consumption value is scaled proportionally to obtain the predicted total energy consumption of the electric wheel dump truck.

[0012] In a preferred embodiment, the step of serializing and arranging the operating condition feature points of the original operating parameter stream of the electric wheel dump truck based on the operating time sequence of the electric wheel dump truck to obtain the operating condition feature sequence of the electric wheel dump truck includes:

[0013] The original operating parameter stream of the electric wheel dump truck is unpacked according to the protocol to obtain the original operating data entries of the electric wheel dump truck;

[0014] Data quality screening is performed on the original operational data entries to obtain a clean operational data sample set of the electric wheel dump truck;

[0015] The timestamp values, vehicle positioning coordinate values, and real-time vehicle speed values ​​are extracted from the clean operation data sample set to construct the working condition feature triplet of the electric wheel dump truck.

[0016] Using the timestamp value as the sorting criterion, the triplets of the working condition features are rearranged in ascending order to obtain the initial sequence of the working condition features of the electric wheel dump truck.

[0017] The time stamp intervals between adjacent triples in the initial sequence of operating conditions are calibrated by equal time intervals to obtain the operating condition feature sequence of the electric wheel dump truck.

[0018] In a preferred embodiment, the step of performing time-series normalization matching between the operating condition feature sequence and the historical operating condition feature sequences in the historical operating condition feature database of the electric wheel dump truck to obtain a reference operating condition feature sequence for the electric wheel dump truck includes:

[0019] Based on the slope level of the working condition feature sequence, the historical working condition feature sequences in the historical working condition feature database of the electric wheel dump truck are filtered and retrieved to obtain the set of historical working condition feature sequences to be matched for the electric wheel dump truck.

[0020] The time-series mapping path of the electric wheel dump truck is obtained by nonlinear scaling path fitting of the working condition feature sequence with the historical working condition feature sequence set to be matched.

[0021] Based on the correspondence in the time-series mapping path, the vehicle speed values ​​in the working condition feature sequence and the vehicle speed values ​​in the historical working condition feature sequence are accumulated point by point to obtain the path accumulation distance of the electric wheel dump truck.

[0022] The cumulative distances along the paths are sorted and compared to obtain a reference working condition characteristic sequence for the electric wheel dump truck.

[0023] In a preferred embodiment, the step of nonlinearly scaling the path of the operating condition feature sequence to the historical operating condition feature sequence set to obtain the time-series mapping path of the electric wheel dump truck includes:

[0024] Using the operating condition feature sequence as a reference template and the historical operating condition feature sequence in the set of historical operating condition feature sequences to be matched as test samples, the cost matrix of the electric wheel dump truck is constructed.

[0025] The cumulative cost matrix of the electric wheel dump truck is obtained by planning and pathfinding on the cost matrix.

[0026] The curved path of the electric wheel dump truck is obtained by backtracking from the direction of minimum cumulative cost in the cumulative cost matrix.

[0027] The feature point indexes in the curved path are paired and encoded with the historical working condition feature sequence to obtain the time-series mapping path of the electric wheel dump truck.

[0028] In a preferred embodiment, the step of performing point-by-point deviation analysis on the vehicle speed values ​​at corresponding time positions in the operating condition feature sequence and the reference operating condition feature sequence, and then weighting and correcting the historical energy consumption records in the historical operating condition feature database based on the accumulated deviation obtained from the analysis to obtain the actual energy consumption benchmark value of the electric wheel dump truck, includes:

[0029] The vehicle speed values ​​at the same mapping node in the working condition feature sequence and the reference working condition feature sequence are extracted synchronously to obtain the real-time vehicle speed sample value and the historical vehicle speed sample value of the electric wheel dump truck.

[0030] The local speed deviation of the electric wheel dump truck is obtained by comparing the real-time vehicle speed sample value with the historical vehicle speed sample value.

[0031] Based on the time-series mapping path of the electric wheel dump truck, the local speed deviation is accumulated and aggregated to obtain the cumulative deviation of the electric wheel dump truck.

[0032] Based on the accumulated deviation, the preset deviation-coefficient mapping table is checked and matched to obtain the weighted correction coefficient of the electric wheel dump truck.

[0033] Historical energy consumption records matching the reference operating condition feature sequence are extracted from the historical operating condition feature database and used as the baseline energy consumption original value of the electric wheel dump truck.

[0034] Based on the weighted correction coefficient, the original baseline energy consumption value is adjusted by weighting to obtain the actual energy consumption baseline value of the electric wheel dump truck.

[0035] In a preferred embodiment, the weighted correction coefficient is calculated using the following formula:

[0036] ;

[0037] In the formula, The weighted correction coefficient is... The preset baseline energy consumption confidence coefficient, For the time-series mapping path, the first Normalized deviation of each mapping node This is the path length factor of the time-series mapping path. The preset time decay factor, Let be the standard deviation of the local vehicle speed deviation. This is the average of the local vehicle speed deviations. It is a natural constant. The index number of the node in the time-series mapping path.

[0038] In a preferred embodiment, the process of dividing the forward path of the electric wheel dump truck into continuous road segment segments based on abrupt changes in slope values ​​in a preset slope map and in conjunction with the actual energy consumption benchmark value, to obtain a slope label for the electric wheel dump truck, includes:

[0039] By performing differential comparisons on the slope values ​​of the preset slope map, the set of slope abrupt change points of the electric wheel dump truck is obtained.

[0040] Based on the deviation between the actual energy consumption benchmark value and the average energy consumption of the same period in the historical working condition feature library, a significance test is performed on the slope change point set to obtain the key slope change point sequence of the electric wheel dump truck.

[0041] Using the sequence of key slope jump points as the road segmentation boundary, the forward path of the electric wheel dump truck is divided into road segments to obtain the main control slope feature value of the electric wheel dump truck.

[0042] The main control slope feature value is graded to obtain the slope label of the electric wheel dump truck.

[0043] In a preferred embodiment, the step of jointly indexing the historical energy consumption records based on the slope label and the load mass signal of the electric wheel dump truck to obtain the basic energy consumption value of the electric wheel dump truck includes:

[0044] Extract the load mass value from the load mass signal of the electric wheel dump truck to obtain the load characteristic value of the electric wheel dump truck;

[0045] Based on the slope level coding of the slope label, the historical working condition feature database is anchored to obtain the historical energy consumption record storage partition of the electric wheel dump truck.

[0046] Using the load characteristic value as the index key, a key-value search is performed on the historical energy consumption record storage partition to obtain the candidate energy consumption record set of the electric wheel dump truck;

[0047] The energy consumption values ​​in the candidate energy consumption record set are fused to obtain the basic energy consumption value of the electric wheel dump truck.

[0048] In a preferred embodiment, the step of scaling the baseline energy consumption value based on the actual energy consumption benchmark value to obtain the predicted total energy consumption of the electric wheel dump truck includes:

[0049] Historical energy consumption records associated with the reference operating condition feature sequence are extracted from the historical operating condition feature database to obtain the benchmark energy consumption reference value of the electric wheel dump truck.

[0050] The scaling factor of the electric wheel dump truck is obtained by calculating the ratio between the actual energy consumption benchmark value and the benchmark energy consumption reference value.

[0051] Based on the scaling factor, the base energy consumption value is weighted and adjusted to obtain the predicted energy consumption component of the electric wheel dump truck.

[0052] The predicted energy consumption components are accumulated and aggregated to obtain the total predicted energy consumption of the electric wheel dump truck.

[0053] To address the aforementioned problems, the present invention also provides an energy consumption prediction system for electric wheel dump trucks based on historical operating conditions, the system comprising:

[0054] The feature serialization module is used to serialize and arrange the working condition feature points of the original operating parameter stream of the electric wheel dump truck based on the running time sequence of the electric wheel dump truck, so as to obtain the working condition feature sequence of the electric wheel dump truck.

[0055] The time-series matching library module is used to perform time-series normalization matching between the working condition feature sequence and the historical working condition feature sequence in the historical working condition feature library of the electric wheel dump truck to obtain the reference working condition feature sequence of the electric wheel dump truck.

[0056] The energy consumption benchmark correction module is used to perform point-by-point deviation analysis on the vehicle speed values ​​at corresponding time positions in the operating condition feature sequence and the reference operating condition feature sequence, and to perform weighted correction on the historical energy consumption record values ​​in the historical operating condition feature library based on the accumulated deviation obtained from the analysis, so as to obtain the actual energy consumption benchmark value of the electric wheel dump truck.

[0057] The road slope labeling module is used to divide the forward path of the electric wheel dump truck into continuous forward road segment segments based on the abrupt change points of the slope value in the preset slope map and in combination with the actual energy consumption benchmark value, so as to obtain the slope label of the electric wheel dump truck.

[0058] The basic energy consumption index module is used to perform a joint indexing of the historical energy consumption record values ​​based on the slope label and the load mass signal of the electric wheel dump truck, so as to obtain the basic energy consumption value of the electric wheel dump truck.

[0059] The total energy consumption prediction module is used to scale the base energy consumption value based on the actual energy consumption benchmark value to obtain the predicted total energy consumption of the electric wheel dump truck.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] 1. This invention serializes and arranges characteristic points of operating conditions based on the running time sequence of electric wheel dump trucks. Through temporal regularization matching, it achieves a precise correspondence between current and historical operating conditions. Combined with point-by-point deviation analysis of vehicle speed values ​​and cumulative deviation, it performs weighted correction of historical energy consumption records, ensuring that the determination of actual energy consumption benchmark values ​​closely matches the real-time operating status of the vehicle. This significantly improves the accuracy of energy consumption benchmark values ​​and lays a realistic calculation foundation for subsequent energy consumption prediction. Simultaneously, relying on slope abrupt change points in a preset slope map, it scientifically divides the path ahead and generates slope labels. Combined with load mass signals, it performs joint indexing of historical energy consumption records, allowing the extraction of basic energy consumption values ​​to be adapted to road slope and vehicle load height, improving the relevance and effectiveness of basic energy consumption values.

[0062] 2. This invention uses the actual energy consumption benchmark as a basis and scales the base energy consumption value proportionally to obtain the predicted total energy consumption. This forms a comprehensive and precise energy consumption prediction system, encompassing the entire process from operating condition feature extraction and historical operating condition matching to energy consumption benchmark correction, road slope labeling, base energy consumption indexing, and total energy consumption prediction. This achieves refined and dynamic prediction of the energy consumption of electric wheel dump trucks, effectively improving the overall accuracy of energy consumption prediction results. Simultaneously, the entire method relies on a historical operating condition feature database to complete multi-dimensional data retrieval and analysis, ensuring that each step of energy consumption prediction is supported by specific operating condition data. This enhances the scientific rigor and systematic nature of the energy consumption prediction process, providing accurate data references for the operational energy consumption management and route scheduling of electric wheel dump trucks. Attached Figure Description

[0063] Figure 1 A flowchart illustrating an embodiment of the present invention provides a method for predicting the energy consumption of an electric wheel dump truck based on historical operating conditions.

[0064] Figure 2 A functional block diagram of an energy consumption prediction system for electric wheel dump trucks based on historical operating conditions, provided in an embodiment of the present invention;

[0065] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0066] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0067] This application provides a method for predicting the energy consumption of electric wheel dump trucks based on historical operating conditions. The execution entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method for predicting the energy consumption of electric wheel dump trucks based on historical operating conditions can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0068] Reference Figure 1 The diagram shown is a flowchart illustrating a method for predicting the energy consumption of an electric wheel dump truck based on historical operating conditions, according to an embodiment of the present invention. In this embodiment, the method for predicting the energy consumption of an electric wheel dump truck based on historical operating conditions includes:

[0069] Pt.1. Based on the running time sequence of the electric wheel dump truck, the working condition feature points of the original running parameter stream in the electric wheel dump truck are serialized and arranged to obtain the working condition feature sequence of the electric wheel dump truck.

[0070] In this embodiment of the invention, the step of serializing and arranging the working condition feature points of the original operating parameter stream of the electric wheel dump truck based on the operating time sequence of the electric wheel dump truck to obtain the working condition feature sequence of the electric wheel dump truck includes:

[0071] The original operating parameter stream of the electric wheel dump truck is unpacked according to the protocol to obtain the original operating data entries of the electric wheel dump truck;

[0072] Data quality screening is performed on the original operational data entries to obtain a clean operational data sample set of the electric wheel dump truck;

[0073] The timestamp values, vehicle positioning coordinate values, and real-time vehicle speed values ​​are extracted from the clean operation data sample set to construct the working condition feature triplet of the electric wheel dump truck.

[0074] Using the timestamp value as the sorting criterion, the triplets of the working condition features are rearranged in ascending order to obtain the initial sequence of the working condition features of the electric wheel dump truck.

[0075] The time stamp intervals between adjacent triples in the initial sequence of operating conditions are calibrated by equal time intervals to obtain the operating condition feature sequence of the electric wheel dump truck.

[0076] According to the established format of the communication protocol of the electric wheel dump truck, the data packets of the original operating parameter stream are parsed frame by frame, and various parameter fields related to vehicle operation are extracted from the data packets. The parameter information of each field is organized according to the preset entry format to form the original operating data entry of the electric wheel dump truck containing complete vehicle operating parameter information.

[0077] Check whether there are any missing fields in the parameter fields of the original operation data entries, determine whether the values ​​of each parameter fall within the preset reasonable range of operating parameters for electric wheel dump trucks, check whether the timestamps of the data entries have duplicate values ​​or out-of-order time sequences, and remove the original operation data entries with missing information, parameter values ​​exceeding the reasonable range, duplicate timestamps, or out-of-order times. The original operation data entries that meet all quality verification standards after verification are centrally summarized to form a clean operation data sample set for electric wheel dump trucks.

[0078] From each clean operation data entry in the clean operation data sample set, the timestamp value, vehicle positioning coordinate value, and real-time vehicle speed value of the preset data location are accurately extracted. The timestamp value, vehicle positioning coordinate value, and real-time vehicle speed value extracted from the same clean operation data entry are associated one by one according to a fixed three-value combination form. Each set of three values ​​after association forms an independent working condition feature triplet for the electric wheel dump truck.

[0079] Extract the corresponding timestamp values ​​from all the working condition feature triples, arrange each working condition feature triple in order of its corresponding timestamp value from earliest to latest, and then continuously integrate all the sorted working condition feature triples in the order of their arrangement to form an initial sequence of working condition features for the electric wheel dump truck with a chronological order.

[0080] A preset standard value for the equal time interval of the electric wheel dump truck's operating condition features is determined. The actual timestamp interval between two adjacent triplets in the initial sequence of operating condition features is calculated. If the actual timestamp interval is greater than the preset standard value, a corresponding number of operating condition feature triplets are added between the two adjacent triplets according to a preset interpolation rule. The timestamp values ​​in the added triplets are evenly distributed according to the standard value of the equal time interval. The vehicle positioning coordinates and real-time speed values ​​are obtained by linear interpolation based on the corresponding values ​​of the two adjacent triplets. If the actual timestamp interval is less than the preset standard value, the operating condition feature triplet with the later timestamp value among the two adjacent triplets is removed. This operation is continued until the timestamp interval between all adjacent triplets in the initial sequence of operating condition features is equal to the preset standard value of the equal time interval. All operating condition feature triplets after the equal time interval calibration are arranged in order to form the operating condition feature sequence of the electric wheel dump truck.

[0081] The beneficial effects are as follows: by unpacking the original operating parameter stream according to the protocol, the original vehicle operation data is effectively parsed and extracted. Then, data quality screening removes various invalid and abnormal operating data, ensuring the basic data quality for subsequent data processing. Subsequently, key parameters are extracted to construct operating condition feature triples, allowing the vehicle operating condition features to be accurately extracted and visualized. Based on the timestamp values, the operating condition feature data is rearranged in ascending order to give the operating condition feature data a clear temporal logic. Then, the time interval between adjacent operating condition feature points is unified through equal time interval calibration, so that the final operating condition feature sequence has the characteristics of data cleanliness, feature relevance, temporal continuity and interval regularity. This provides standardized and high-quality basic data support for subsequent energy consumption prediction operations such as operating condition matching and energy consumption benchmark correction for electric wheel dump trucks, ensuring the orderly development of the subsequent energy consumption prediction process and the accuracy of the results from the data source.

[0082] Pt.2. Perform time-series normalization matching between the operating condition feature sequence and the historical operating condition feature sequence in the historical operating condition feature library of the electric wheel dump truck to obtain the reference operating condition feature sequence of the electric wheel dump truck.

[0083] In this embodiment of the invention, the step of performing time-series normalization matching between the operating condition feature sequence and the historical operating condition feature sequence in the historical operating condition feature database of the electric wheel dump truck to obtain the reference operating condition feature sequence of the electric wheel dump truck includes:

[0084] Based on the slope level of the working condition feature sequence, the historical working condition feature sequences in the historical working condition feature database of the electric wheel dump truck are filtered and retrieved to obtain the set of historical working condition feature sequences to be matched for the electric wheel dump truck.

[0085] The time-series mapping path of the electric wheel dump truck is obtained by nonlinear scaling path fitting of the working condition feature sequence with the historical working condition feature sequence set to be matched.

[0086] Based on the correspondence in the time-series mapping path, the vehicle speed values ​​in the working condition feature sequence and the vehicle speed values ​​in the historical working condition feature sequence are accumulated point by point to obtain the path accumulation distance of the electric wheel dump truck.

[0087] The cumulative distances along the paths are sorted and compared to obtain a reference working condition characteristic sequence for the electric wheel dump truck.

[0088] The step of fitting the nonlinear scaling path of the operating condition feature sequence to the historical operating condition feature sequence set to obtain the time-series mapping path of the electric wheel dump truck includes:

[0089] Using the operating condition feature sequence as a reference template and the historical operating condition feature sequence in the set of historical operating condition feature sequences to be matched as test samples, the cost matrix of the electric wheel dump truck is constructed.

[0090] The cumulative cost matrix of the electric wheel dump truck is obtained by planning and pathfinding on the cost matrix.

[0091] The curved path of the electric wheel dump truck is obtained by backtracking from the direction of minimum cumulative cost in the cumulative cost matrix.

[0092] The feature point indexes in the curved path are paired and encoded with the historical working condition feature sequence to obtain the time-series mapping path of the electric wheel dump truck.

[0093] The vehicle positioning coordinates of each feature node in the working condition feature sequence are extracted. Combined with the preset electronic topographic map, the actual slope value corresponding to each positioning coordinate is matched. According to the preset slope level classification rules, each slope value is assigned to the corresponding slope level interval. The overall slope level of the working condition feature sequence is determined by comprehensively considering the slope level distribution of all feature nodes. All historical working condition feature sequences in the historical working condition feature database of electric wheel dump trucks are traversed. The overall slope level information of each historical working condition feature sequence is extracted. All historical working condition feature sequences that are consistent with the overall slope level of the current working condition feature sequence are retrieved and centrally organized to obtain the set of historical working condition feature sequences to be matched for electric wheel dump trucks.

[0094] Using the working condition feature sequence as a fixed reference template, each historical working condition feature sequence in the set of historical working condition feature sequences to be matched is taken as an independent test sample. First, the starting and ending feature nodes of the reference template and a single test sample are aligned. The total number of feature nodes of the reference template and the test sample is counted. If the number of nodes of the test sample is more than that of the reference template, some feature nodes of the test sample are removed according to the equal interval rule. If the number of nodes of the test sample is less than that of the reference template, the corresponding number of feature nodes are added to the test sample according to the linear interpolation rule to make the total number of feature nodes of the two consistent. Then, the similarity of vehicle speed features is compared for each aligned feature node. The correspondence between nodes is adjusted according to the similarity results to form a curved fitting trajectory that fits the feature changes of both. The one-to-one correspondence index information of the working condition feature sequence and the historical working condition feature sequence feature nodes in the trajectory is completely recorded to obtain the time-series mapping path of the electric wheel dump truck.

[0095] Based on the correspondence of feature nodes recorded in the time-series mapping path, the real-time vehicle speed value and historical vehicle speed value of each group of corresponding feature nodes are extracted synchronously from the working condition feature sequence and the corresponding historical working condition feature sequence. The difference operation is performed on the two corresponding vehicle speed values ​​of each group and the absolute value of the operation result is taken to obtain the vehicle speed difference value of the corresponding node of that group. From the starting feature node to the ending feature node of the time-series mapping path, the vehicle speed difference values ​​of all groups of corresponding nodes are continuously accumulated in the order of node arrangement. The sum obtained after accumulation is used as the path accumulation distance of the electric wheel dump truck.

[0096] Collect the cumulative path distances obtained by performing nonlinear scaling path fitting between each historical working condition feature sequence and the working condition feature sequence in the set of historical working condition feature sequences to be matched. Arrange all the cumulative path distances in ascending order of value, and simultaneously record the historical working condition feature sequences corresponding to each cumulative path distance. Select the historical working condition feature sequence corresponding to the cumulative path distance with the smallest value in the arrangement results, and determine it as the reference working condition feature sequence for the electric wheel dump truck.

[0097] Using the working condition feature sequence as a reference template and counting the total number of feature points it contains, a single historical working condition feature sequence from the set of historical working condition feature sequences to be matched is used as a test sample and the total number of feature points it contains is counted. The feature points of the reference template are used as row dimension identifiers of the matrix, and the feature points of the test samples are used as column dimension identifiers of the matrix. A two-dimensional matrix framework matching the number of feature points is constructed. The absolute value of the difference between the real-time vehicle speed value of each feature point in the reference template and each feature point in the test sample is calculated. This absolute value is used as the element value at the intersection of the corresponding row and column in the two-dimensional matrix framework. The two-dimensional matrix formed after filling all the element values ​​at the intersection is the cost matrix of the electric wheel dump truck.

[0098] Retaining the row and column dimension identifiers of the cost matrix, construct a cumulative cost matrix framework of the same dimension. Directly fill the element value of the first row and first column of the cost matrix into the same position of the cumulative cost matrix. Starting from the second column of the first row, sequentially add the element value to the left of the current position in the cumulative cost matrix to the element value of the current position in the cost matrix, and fill the corresponding position in the cumulative cost matrix with the result. This completes the filling of all elements in the first row. Starting from the first column of the second row, sequentially add the element value above the current position in the cumulative cost matrix to the element value of the current position in the cost matrix, and fill the corresponding position in the cumulative cost matrix with the result. This completes the filling of all elements in the first column. For the remaining positions, extract the element values ​​of the three positions to the left, top, and top left of the current position in the cumulative cost matrix, select the minimum value among them, add it to the element value of the current position in the cost matrix, and fill the corresponding position in the cumulative cost matrix with the result. After completing the numerical filling of all positions, the cumulative cost matrix of the electric wheel dump truck is obtained.

[0099] The last row and last column of the cumulative cost matrix is ​​determined as the backtracking starting point. The element value at this position is extracted as the current cumulative cost baseline value. Starting from the starting point, the element values ​​at the left, top, and upper left positions of the current position are extracted in sequence. The three values ​​are compared with the current cumulative cost baseline value, and the minimum value is selected. The position corresponding to the minimum value is determined as the next backtracking node. If two or more positions have the same element value and all are the minimum value, the upper left position is directly selected as the next backtracking node. The element value of the new backtracking node is updated with the current cumulative cost baseline value, and the above node selection operation is repeated until the backtracking operation reaches the first row and first column of the cumulative cost matrix. All the backtracking nodes are arranged in the order of the backtracking operation. The continuous trajectory formed by connecting the coordinates of the arranged nodes in sequence is the bending path of the electric wheel dump truck.

[0100] Extract the reference templates corresponding to all nodes in the curved path, i.e., the feature point index numbers of the working condition feature sequence. At the same time, extract the test samples corresponding to each node, i.e., the feature point index numbers of the historical working condition feature sequence. Bind each pair of corresponding working condition feature sequence feature point index numbers to the historical working condition feature sequence feature point index numbers to form an independent index pairing group. Arrange all independent index pairing groups in a continuous and orderly manner according to the order of nodes in the curved path. Encode the arranged index pairing groups uniformly. The encoded content completely retains the correspondence of each index group and the overall arrangement order. The ordered index pairing set formed after encoding is the time-series mapping path of the electric wheel dump truck.

[0101] The beneficial effects are that by selectively filtering the historical working condition feature database based on the slope level of the working condition feature sequence, the scope of working condition matching is effectively narrowed, the processing volume of subsequent matching operations is reduced, and the efficiency of overall time-series regularization matching is improved. At the same time, the historical working condition feature sequence to be matched is adapted to the current working condition in terms of slope dimension, laying the foundation for subsequent accurate matching.

[0102] By constructing a cost matrix using the working condition feature sequence as a reference template and the historical working condition feature sequence as a test sample, and then obtaining the cumulative cost matrix through path planning, a curved path is obtained by backtracking from the direction of minimum cumulative cost and completing the feature point index pairing encoding to form a time-series mapping path. This achieves accurate nonlinear scaling path fitting between the working condition feature sequence and the historical working condition feature sequence, allowing sequences with different time lengths and feature changes to form accurate feature point correspondences, thus ensuring the accuracy and fit of the time-series mapping path.

[0103] Based on the correspondence of time-series mapping paths, the cumulative distance of the path is obtained by accumulating the point-by-point differences of vehicle speed values. This objectively quantifies the similarity between the current operating condition feature sequence and each historical operating condition feature sequence. By sorting and comparing the cumulative distance of the path, a reference operating condition feature sequence is selected. This accurately filters out the historical sequence with the highest similarity to the current operating condition feature sequence, ensuring that the final reference operating condition feature sequence has a high degree of matching. This provides an accurate and reliable operating condition reference for the subsequent correction of the energy consumption benchmark of electric wheel dump trucks and the overall energy consumption prediction, ensuring the accuracy of the energy consumption prediction results from the perspective of operating condition matching.

[0104] Pt.3. Perform point-by-point deviation analysis on the vehicle speed values ​​at corresponding time positions in the operating condition feature sequence and the reference operating condition feature sequence, and perform weighted correction on the historical energy consumption record values ​​of the historical operating condition feature library based on the accumulated deviation obtained from the analysis, so as to obtain the actual energy consumption benchmark value of the electric wheel dump truck.

[0105] In this embodiment of the invention, the step of performing point-by-point deviation analysis on the vehicle speed values ​​at corresponding time positions in the operating condition feature sequence and the reference operating condition feature sequence, and then weighting and correcting the historical energy consumption records in the historical operating condition feature database based on the accumulated deviation obtained from the analysis to obtain the actual energy consumption benchmark value of the electric wheel dump truck, includes:

[0106] The vehicle speed values ​​at the same mapping node in the working condition feature sequence and the reference working condition feature sequence are extracted synchronously to obtain the real-time vehicle speed sample value and the historical vehicle speed sample value of the electric wheel dump truck.

[0107] The local speed deviation of the electric wheel dump truck is obtained by comparing the real-time vehicle speed sample value with the historical vehicle speed sample value.

[0108] Based on the time-series mapping path of the electric wheel dump truck, the local speed deviation is accumulated and aggregated to obtain the cumulative deviation of the electric wheel dump truck.

[0109] Based on the accumulated deviation, the preset deviation-coefficient mapping table is checked and matched to obtain the weighted correction coefficient of the electric wheel dump truck.

[0110] Historical energy consumption records matching the reference operating condition feature sequence are extracted from the historical operating condition feature database and used as the baseline energy consumption original value of the electric wheel dump truck.

[0111] Based on the weighted correction coefficient, the original baseline energy consumption value is adjusted by weighting to obtain the actual energy consumption baseline value of the electric wheel dump truck.

[0112] The formula for calculating the weighted correction coefficient is as follows:

[0113] ;

[0114] In the formula, The weighted correction coefficient is... The preset baseline energy consumption confidence coefficient, For the time-series mapping path, the first Normalized deviation of each mapping node This is the path length factor of the time-series mapping path. The preset time decay factor, Let be the standard deviation of the local vehicle speed deviation. This is the average of the local vehicle speed deviations. It is a natural constant. The index number of the node in the time-series mapping path.

[0115] Based on the correspondence of feature points recorded in the time-series mapping path of the electric wheel dump truck, each mapping node in the path is traversed. The vehicle speed value corresponding to each mapping node is extracted from the working condition feature sequence as the real-time vehicle speed sample value. At the same time, the vehicle speed value corresponding to the same mapping node is extracted from the reference working condition feature sequence as the historical vehicle speed sample value. The real-time vehicle speed sample value and the historical vehicle speed sample value corresponding to each mapping node are stored one-to-one to form a complete set of sample value correspondences, thus obtaining the real-time vehicle speed sample value and the historical vehicle speed sample value of the electric wheel dump truck.

[0116] For each set of real-time and historical vehicle speed samples in the sample value correspondence set, a subtraction operation is performed. The real-time vehicle speed sample value is used as the minuend and the historical vehicle speed sample value is used as the subtrahend. The difference obtained from each set of operations is used as the local vehicle speed deviation of the corresponding mapping node. The local vehicle speed deviation of all mapping nodes is recorded in sequence according to the order of the mapping nodes in the time-series mapping path to obtain the local vehicle speed deviation of the electric wheel dump truck.

[0117] According to the sequential arrangement of the mapping nodes in the time-series mapping path, starting from the local vehicle speed deviation corresponding to the first mapping node, the local vehicle speed deviation of each subsequent mapping node is continuously accumulated with the previous accumulation result. The calculation result of each step is completely retained during the accumulation process until the accumulation operation of the local vehicle speed deviation of the last mapping node is completed. The final accumulated sum is used as the deviation accumulation of the electric wheel dump truck.

[0118] The preset deviation-coefficient mapping table pre-sets continuous and non-overlapping deviation accumulation value ranges. Each value range uniquely corresponds to a fixed coefficient value. First, it is determined which value range in the mapping table the calculated deviation accumulation falls into. Then, the fixed coefficient value corresponding to that value range is accurately retrieved from the mapping table. The retrieved coefficient value is the weighted correction coefficient of the electric wheel dump truck.

[0119] In the historical operating condition feature database of electric wheel dump trucks, all historical operating condition feature sequences are uniquely associated with their historical energy consumption records generated during actual operation. Based on the unique identification information of the determined reference operating condition feature sequence, a precise retrieval operation is performed in the historical operating condition feature database to retrieve the historical energy consumption record value that is uniquely associated with the reference operating condition feature sequence. The retrieved value is used as the baseline energy consumption original value of the electric wheel dump truck.

[0120] The extracted baseline energy consumption value is multiplied by the matched weighted correction coefficient. The complete numerical calculation process is completed according to the basic calculation rules of numerical multiplication. The product value obtained after the calculation is recorded and stored. This product value is the actual energy consumption baseline value of the electric wheel dump truck.

[0121] The basic energy consumption confidence coefficient is a pre-set fixed value. The normalized deviation is obtained by normalizing the local vehicle speed deviation corresponding to each mapping node in the time-series mapping path. The path length factor is the total number of mapping nodes included in the time-series mapping path. The time decay factor is a pre-set fixed value. The node index number is a unique number assigned to each mapping node in the time-series mapping path according to the order of arrangement. The standard deviation of the local vehicle speed deviation is a value obtained after calculating the dispersion of the local vehicle speed deviation of all mapping nodes. The mean of the local vehicle speed deviation is a value obtained after calculating the average of the local vehicle speed deviation of all mapping nodes. The natural constant is a fixed mathematical constant. All values ​​are obtained or pre-set in relation to the vehicle speed deviation analysis process of the working condition characteristic sequence of the electric wheel dump truck and the reference working condition characteristic sequence.

[0122] The core significance of this calculation is that by integrating various factors related to vehicle speed deviation, such as the vehicle speed deviation characteristics, the discrete and average characteristics of deviation values, and the time decay characteristics of each mapping node in the time-series mapping path, the confidence coefficient of the basic energy consumption is adjusted with targeted weighting. Finally, a weighted correction coefficient that can accurately reflect the degree of vehicle speed deviation between the real-time operating conditions and the reference operating conditions of the electric wheel dump truck is obtained. This coefficient can be directly used to adjust the original value of the benchmark energy consumption, so that the actual energy consumption benchmark value obtained after adjustment can fit the real-time operating conditions of the electric wheel dump truck. From the perspective of vehicle speed deviation, the historical energy consumption record value is accurately corrected, providing an energy consumption benchmark that fits the actual operating state for subsequent energy consumption prediction of electric wheel dump trucks.

[0123] The beneficial effects are that the acquisition and setting of various values ​​are all carried out around the core process of speed deviation analysis of the electric wheel dump truck's operating condition characteristic sequence and reference operating condition characteristic sequence. This ensures the relevance and rationality of the data source used for the weighted correction coefficient calculation. Each value corresponds to a different characteristic dimension of the speed deviation, allowing the coefficient calculation to comprehensively integrate various key elements related to the speed deviation. This enables targeted weighted adjustment of the basic energy consumption confidence coefficient, thereby obtaining a weighted correction coefficient that accurately reflects the degree of speed deviation between the real-time operating condition and the reference operating condition. By using this coefficient to weight and adjust the original baseline energy consumption value, the final actual energy consumption baseline value can closely match the real-time operating condition of the electric wheel dump truck. From the perspective of speed deviation, it completes the accurate correction of historical energy consumption records, effectively improving the accuracy and fit of the energy consumption baseline value. This provides a reliable energy consumption baseline that fits the actual operating state for subsequent energy consumption prediction of electric wheel dump trucks, ensuring the accuracy of subsequent overall energy consumption prediction results from the perspective of energy consumption baseline.

[0124] Pt.4. Based on the abrupt change points of the slope value in the preset slope map and combined with the actual energy consumption benchmark value, the forward path of the electric wheel dump truck is divided into continuous forward road segment segments to obtain the slope label of the electric wheel dump truck.

[0125] In this embodiment of the invention, the method of dividing the forward path of the electric wheel dump truck into continuous forward road segments based on the abrupt change points of the slope values ​​in the preset slope map and in combination with the actual energy consumption benchmark value, to obtain the slope label of the electric wheel dump truck, includes:

[0126] By performing differential comparisons on the slope values ​​of the preset slope map, the set of slope abrupt change points of the electric wheel dump truck is obtained.

[0127] Based on the deviation between the actual energy consumption benchmark value and the average energy consumption of the same period in the historical working condition feature library, a significance test is performed on the slope change point set to obtain the key slope change point sequence of the electric wheel dump truck.

[0128] Using the sequence of key slope jump points as the road segmentation boundary, the forward path of the electric wheel dump truck is divided into road segments to obtain the main control slope feature value of the electric wheel dump truck.

[0129] The main control slope feature value is graded to obtain the slope label of the electric wheel dump truck.

[0130] According to the spatial extension order of the path ahead of the electric wheel dump truck, the slope values ​​of the corresponding path positions are extracted sequentially from the preset slope map. The slope values ​​of two adjacent positions are calculated by subtracting the preceding term from the following term. The absolute value of the result is taken as the slope difference between adjacent positions. A fixed slope difference threshold is preset. Path positions with slope differences greater than the threshold are marked as slope abrupt change points. All the marked slope abrupt change points are sorted and summarized according to their spatial order in the path ahead to obtain the slope abrupt change point set of the electric wheel dump truck.

[0131] Historical energy consumption records with the same operating period and slope level as the current operating condition are extracted from the historical operating condition feature database of the electric wheel dump truck. The arithmetic mean of these historical energy consumption records is calculated to obtain the historical average energy consumption for the same period. The difference between the actual energy consumption benchmark value and the historical average energy consumption for the same period is calculated to obtain the deviation value. The deviation value is divided by the historical average energy consumption for the same period to obtain the actual deviation range. A fixed deviation range threshold is preset. The slope change corresponding to each slope change point in the slope change point set is combined with the deviation range for verification. Only the slope change points corresponding to the deviation range are retained. The slope change points that have been verified and retained are arranged in spatial order in the forward path to obtain the key slope change point sequence of the electric wheel dump truck.

[0132] Each critical slope transition point in the critical slope transition point sequence is marked according to its actual spatial position in the path ahead of the electric wheel dump truck. Using two adjacent critical slope transition points as boundaries, the path between the two boundaries is divided into independent forward road segments. At the same time, the path from the start position of the forward road to the first critical slope transition point and the path from the last critical slope transition point to the end position of the forward road are also divided into independent forward road segments. The arithmetic mean of the slope values ​​corresponding to all path positions in each independent forward road segment is calculated, and the calculated average value is determined as the main control slope feature value of the corresponding forward road segment, thus obtaining the main control slope feature value of the electric wheel dump truck.

[0133] A slope grade classification standard with continuous and non-overlapping intervals is preset. A unique fixed code is assigned to each slope grade interval. The code consists of a combination of numbers and letters, and each code corresponds to a unique slope grade interval. The main control slope feature value of each road segment ahead is compared with the slope grade classification standard to determine the specific slope grade interval to which it belongs. The fixed code corresponding to that interval is retrieved as the slope grade code of that road segment ahead. According to the spatial arrangement order of each road segment ahead in the path ahead of the electric wheel dump truck, the slope grade codes corresponding to each segment are continuously and orderly combined. The combined code set is the slope label of the electric wheel dump truck.

[0134] The beneficial effect is that by performing a step-by-step difference comparison of the slope values ​​in the preset slope map, the locations where the slope changes significantly in the path ahead of the electric wheel dump truck can be accurately identified, forming a complete set of slope abrupt change points. This provides a basic location basis for the segmentation of the path ahead. By combining the deviation of the actual energy consumption benchmark value with the historical average energy consumption value for the same period to conduct a significance test on the slope abrupt change point set, key slope jump points related to actual energy consumption conditions can be screened out. This makes the boundary of the road segmentation more closely match the actual operating energy consumption requirements of the electric wheel dump truck, avoiding interference from invalid slope abrupt change points on the road segmentation. The key slope jump point sequence is used as the boundary... Dividing the path ahead into sections ensures that the resulting road segments have consistent slope characteristics. By calculating the main control slope feature values ​​of each segment, the core slope attributes of each segment can be accurately represented. Grading the main control slope feature values ​​into slope labels transforms the slope characteristics of each segment into standardized and structured identification information. This facilitates subsequent joint indexing of historical energy consumption records by combining them with load mass signals. This provides accurate, standardized, and practical slope dimension basis for obtaining subsequent basic energy consumption values. From the perspective of path slope feature processing, this ensures the efficiency and accuracy of subsequent energy consumption prediction operations.

[0135] Pt.5. Based on the slope label and the load mass signal of the electric wheel dump truck, the historical energy consumption record value is jointly indexed to obtain the basic energy consumption value of the electric wheel dump truck.

[0136] In this embodiment of the invention, the step of jointly indexing the historical energy consumption records based on the slope label and the load mass signal of the electric wheel dump truck to obtain the basic energy consumption value of the electric wheel dump truck includes:

[0137] Extract the load mass value from the load mass signal of the electric wheel dump truck to obtain the load characteristic value of the electric wheel dump truck;

[0138] Based on the slope level coding of the slope label, the historical working condition feature database is anchored to obtain the historical energy consumption record storage partition of the electric wheel dump truck.

[0139] Using the load characteristic value as the index key, a key-value search is performed on the historical energy consumption record storage partition to obtain the candidate energy consumption record set of the electric wheel dump truck;

[0140] The energy consumption values ​​in the candidate energy consumption record set are fused to obtain the basic energy consumption value of the electric wheel dump truck.

[0141] The continuously collected real-time load mass values ​​are extracted from the load mass signal of the electric wheel dump truck. Invalid values ​​that are zero or exceed the preset load capacity range of the electric wheel dump truck are removed. The remaining valid load mass values ​​are then calculated by arithmetic average, and the calculated average value is used as the load characteristic value of the electric wheel dump truck.

[0142] The historical operating condition feature database of electric wheel dump trucks is structured and partitioned according to the slope level code. Each storage partition is identified by a unique slope level code. All slope level codes contained in the slope tag are extracted, and a precise search is performed in the historical operating condition feature database based on the code. All storage partitions that match the code are integrated and collected to obtain the historical energy consumption record storage partition of the electric wheel dump truck.

[0143] All historical energy consumption records in the historical energy consumption record storage partition are associated with fixed key values ​​and corresponding load values. A load value matching interval is preset to match the rated load value range of the electric wheel dump truck. The load feature value is included in this interval for matching and retrieval. All historical energy consumption records in the historical energy consumption record storage partition whose key values ​​are within the matching interval are extracted. All extracted historical energy consumption records are sorted in order according to their actual operation and storage time to obtain the candidate energy consumption record set of the electric wheel dump truck.

[0144] The validity of all energy consumption values ​​in the candidate energy consumption record set is verified. Abnormal energy consumption values ​​that exceed the preset reasonable range of energy consumption for a single road segment operation of the electric wheel dump truck are removed. The arithmetic average of all valid energy consumption values ​​remaining after verification is calculated, and the calculated average value is recorded completely. This value is the basic energy consumption value of the electric wheel dump truck.

[0145] The beneficial effects are as follows: By numerically extracting and processing the load mass signal of the electric wheel dump truck, load feature values ​​are obtained, accurately extracting the core features of the vehicle's load dimension. This provides a load basis that fits the actual operating state of the vehicle for the indexing of energy consumption records. Anchoring the historical operating condition feature database based on the slope level code of the slope label can quickly locate the historical energy consumption record storage partition that matches the current path slope features, significantly narrowing the retrieval scope of energy consumption records and improving the efficiency of indexing operations. At the same time, it ensures that the retrieval scope is highly adapted to the current slope operating conditions, using load feature values ​​as index keywords for anchoring. The storage partition is used for key-value retrieval, allowing the selected candidate energy consumption record set to simultaneously match the dual core operating conditions of the current vehicle, namely slope and load. This avoids interference from irrelevant energy consumption records. The energy consumption values ​​of the candidate energy consumption record set are then fused to eliminate abnormal values ​​and integrate effective energy consumption data, resulting in a basic energy consumption value that accurately reflects the basic energy consumption level under the current operating conditions. This provides accurate basic energy consumption data support for the subsequent calculation of the total predicted energy consumption of electric wheel dump trucks, ensuring the accuracy and reliability of subsequent energy consumption prediction results from the perspective of energy consumption data retrieval and integration.

[0146] Pt.6. Based on the actual energy consumption benchmark value, the basic energy consumption value is scaled proportionally to obtain the predicted total energy consumption of the electric wheel dump truck.

[0147] In this embodiment of the invention, the step of scaling the base energy consumption value based on the actual energy consumption benchmark value to obtain the predicted total energy consumption of the electric wheel dump truck includes:

[0148] Historical energy consumption records associated with the reference operating condition feature sequence are extracted from the historical operating condition feature database to obtain the benchmark energy consumption reference value of the electric wheel dump truck.

[0149] The scaling factor of the electric wheel dump truck is obtained by calculating the ratio between the actual energy consumption benchmark value and the benchmark energy consumption reference value.

[0150] Based on the scaling factor, the base energy consumption value is weighted and adjusted to obtain the predicted energy consumption component of the electric wheel dump truck.

[0151] The predicted energy consumption components are accumulated and aggregated to obtain the total predicted energy consumption of the electric wheel dump truck.

[0152] Historical energy consumption records that are uniquely associated with the reference operating condition sequence are retrieved from the historical operating condition feature database of the electric wheel dump truck. These historical energy consumption records are the actual operating energy consumption data corresponding to the reference operating condition feature sequence. The retrieved values ​​are directly determined as the benchmark energy consumption reference values ​​for the electric wheel dump truck.

[0153] The actual energy consumption benchmark value of the electric wheel dump truck is used as the dividend, and the benchmark energy consumption reference value is used as the divisor. A numerical division operation is performed, and the calculated quotient result is completely retained during the operation. This quotient result is the scaling factor of the electric wheel dump truck.

[0154] The basic energy consumption value corresponding to each road segment ahead of the electric wheel dump truck is multiplied by the scaling factor. The calculation process of each basic energy consumption value and scaling factor is completed according to the basic calculation rules of multiplication. The product value obtained after each calculation is determined as the predicted energy consumption component of the electric wheel dump truck for the corresponding road segment ahead.

[0155] According to the spatial arrangement of each road segment in the path ahead of the electric wheel dump truck, starting from the predicted energy consumption component of the first road segment, the predicted energy consumption component of each subsequent road segment is continuously added to the previous accumulated result until the accumulation operation of the predicted energy consumption component of the last road segment is completed. The final accumulated sum is determined as the total predicted energy consumption of the electric wheel dump truck.

[0156] The beneficial effects include extracting benchmark energy consumption reference values ​​associated with the reference operating condition feature sequence from the historical operating condition feature database, ensuring a strong correlation between the data source for energy consumption ratio calculation and the reference operating condition, providing an accurate historical energy consumption benchmark for obtaining the scaling factor, and obtaining the scaling factor by comparing the actual energy consumption benchmark value with the benchmark energy consumption reference value. This accurately quantifies the change in the current actual energy consumption benchmark relative to the historical reference energy consumption benchmark, allowing subsequent weighting adjustments to have a quantitative basis that fits the real-time operating conditions of the vehicle. Based on the scaling factor, the weighted adjustment of the basic energy consumption value yields the predicted energy consumption component. This system transforms basic energy consumption values ​​into benchmarks that align with current actual energy consumption, ensuring that the predicted energy consumption values ​​for each road segment ahead are adapted to the real-time operating conditions of the vehicle. By accumulating and aggregating the predicted energy consumption components, the system obtains the total predicted energy consumption. It comprehensively integrates the energy consumption prediction results for each road segment ahead, forming a predicted value that reflects the overall energy consumption level of the vehicle's path. This value integrates various vehicle operating condition characteristics such as gradient, load, and speed deviation, ensuring that the final energy consumption prediction result is both accurate and complete. This provides a reliable quantitative data basis for subsequent work such as energy consumption management and operation scheduling of electric wheel dump trucks.

[0157] like Figure 2The diagram shown is a functional block diagram of an electric wheel dump truck energy consumption prediction system based on historical operating conditions, provided by an embodiment of the present invention.

[0158] The energy consumption prediction system for electric wheel dump trucks based on historical operating conditions described in this invention can be installed in an electronic device. Depending on the functions implemented, the system may include a feature serialization module, a time-series matching library module, an energy consumption benchmark correction module, a road slope labeling module, a basic energy consumption index module, and a total energy consumption prediction module. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, stored in the memory of the electronic device.

[0159] In this embodiment, the functions of each module / unit are as follows:

[0160] The feature serialization module is used to serialize and arrange the working condition feature points of the original operating parameter stream of the electric wheel dump truck based on the running time sequence of the electric wheel dump truck, so as to obtain the working condition feature sequence of the electric wheel dump truck.

[0161] The time-series matching library module is used to perform time-series normalization matching between the working condition feature sequence and the historical working condition feature sequence in the historical working condition feature library of the electric wheel dump truck to obtain the reference working condition feature sequence of the electric wheel dump truck.

[0162] The energy consumption benchmark correction module is used to perform point-by-point deviation analysis on the vehicle speed values ​​at corresponding time positions in the operating condition feature sequence and the reference operating condition feature sequence, and to perform weighted correction on the historical energy consumption record values ​​in the historical operating condition feature library based on the accumulated deviation obtained from the analysis, so as to obtain the actual energy consumption benchmark value of the electric wheel dump truck.

[0163] The road slope labeling module is used to divide the forward path of the electric wheel dump truck into continuous forward road segment segments based on the abrupt change points of the slope value in the preset slope map and in combination with the actual energy consumption benchmark value, so as to obtain the slope label of the electric wheel dump truck.

[0164] The basic energy consumption index module is used to perform a joint indexing of the historical energy consumption record values ​​based on the slope label and the load mass signal of the electric wheel dump truck, so as to obtain the basic energy consumption value of the electric wheel dump truck.

[0165] The total energy consumption prediction module is used to scale the base energy consumption value based on the actual energy consumption benchmark value to obtain the predicted total energy consumption of the electric wheel dump truck.

[0166] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0167] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0168] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0169] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0170] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0171] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for predicting the energy consumption of electric wheel dump trucks based on historical operating conditions, characterized in that, The method includes: Pt.

1. Based on the running time sequence of the electric wheel dump truck, the working condition feature points of the original running parameter stream in the electric wheel dump truck are serialized and arranged to obtain the working condition feature sequence of the electric wheel dump truck. Pt.

2. Perform time-series normalization matching between the operating condition feature sequence and the historical operating condition feature sequence in the historical operating condition feature library of the electric wheel dump truck to obtain the reference operating condition feature sequence of the electric wheel dump truck. Pt.

3. Perform point-by-point deviation analysis on the vehicle speed values ​​at corresponding time positions in the operating condition feature sequence and the reference operating condition feature sequence, and based on the accumulated deviation obtained from the analysis, perform weighted correction on the historical energy consumption records in the historical operating condition feature database to obtain the actual energy consumption benchmark value of the electric wheel dump truck, including: The vehicle speed values ​​at the same mapping node in the working condition feature sequence and the reference working condition feature sequence are extracted synchronously to obtain the real-time vehicle speed sample value and the historical vehicle speed sample value of the electric wheel dump truck. The local speed deviation of the electric wheel dump truck is obtained by comparing the real-time vehicle speed sample value with the historical vehicle speed sample value. Based on the time-series mapping path of the electric wheel dump truck, the local speed deviation is accumulated and aggregated to obtain the cumulative deviation of the electric wheel dump truck. Based on the accumulated deviation, the preset deviation-coefficient mapping table is checked and matched to obtain the weighted correction coefficient of the electric wheel dump truck. Historical energy consumption records matching the reference operating condition feature sequence are extracted from the historical operating condition feature database and used as the baseline energy consumption original value of the electric wheel dump truck. Based on the weighted correction coefficient, the original value of the benchmark energy consumption is adjusted by weighting to obtain the actual energy consumption benchmark value of the electric wheel dump truck. Pt.

4. Based on the abrupt change points of slope values ​​in the preset slope map, and combined with the actual energy consumption benchmark value, the forward path of the electric wheel dump truck is divided into continuous forward road segment segments to obtain the slope label of the electric wheel dump truck, including: By performing differential comparisons on the slope values ​​of the preset slope map, the set of slope abrupt change points of the electric wheel dump truck is obtained. Based on the deviation between the actual energy consumption benchmark value and the average energy consumption of the same period in the historical working condition feature library, a significance test is performed on the slope change point set to obtain the key slope change point sequence of the electric wheel dump truck. Using the sequence of key slope jump points as the road segmentation boundary, the forward path of the electric wheel dump truck is divided into road segments to obtain the main control slope feature value of the electric wheel dump truck. The main control slope feature value is graded to obtain the slope label of the electric wheel dump truck; Pt.

5. Based on the slope label and the load mass signal of the electric wheel dump truck, the historical energy consumption record value is jointly indexed to obtain the basic energy consumption value of the electric wheel dump truck. Pt.

6. Based on the actual energy consumption benchmark value, the basic energy consumption value is scaled proportionally to obtain the predicted total energy consumption of the electric wheel dump truck.

2. The method for predicting the energy consumption of electric wheel dump trucks based on historical operating conditions as described in claim 1, characterized in that, Based on the operating time sequence of the electric wheel dump truck, the working condition feature points of the original operating parameter stream of the electric wheel dump truck are serialized and arranged to obtain the working condition feature sequence of the electric wheel dump truck, including: The original operating parameter stream of the electric wheel dump truck is unpacked according to the protocol to obtain the original operating data entries of the electric wheel dump truck; Data quality screening is performed on the original operational data entries to obtain a clean operational data sample set of the electric wheel dump truck; The timestamp values, vehicle positioning coordinate values, and real-time vehicle speed values ​​are extracted from the clean operation data sample set to construct the working condition feature triplet of the electric wheel dump truck. Using the timestamp value as the sorting criterion, the triplets of the working condition features are rearranged in ascending order to obtain the initial sequence of the working condition features of the electric wheel dump truck. The time stamp intervals between adjacent triples in the initial sequence of operating conditions are calibrated by equal time intervals to obtain the operating condition feature sequence of the electric wheel dump truck.

3. The method for predicting the energy consumption of electric wheel dump trucks based on historical operating conditions as described in claim 1, characterized in that, The step of performing time-series normalization matching between the operating condition feature sequence and the historical operating condition feature sequence in the historical operating condition feature database of the electric wheel dump truck to obtain the reference operating condition feature sequence of the electric wheel dump truck includes: Based on the slope level of the working condition feature sequence, the historical working condition feature sequences in the historical working condition feature database of the electric wheel dump truck are filtered and retrieved to obtain the set of historical working condition feature sequences to be matched for the electric wheel dump truck. The time-series mapping path of the electric wheel dump truck is obtained by nonlinear scaling path fitting of the working condition feature sequence with the historical working condition feature sequence set to be matched. Based on the correspondence in the time-series mapping path, the vehicle speed values ​​in the working condition feature sequence and the vehicle speed values ​​in the historical working condition feature sequence are accumulated point by point to obtain the path accumulation distance of the electric wheel dump truck. The cumulative distances along the paths are sorted and compared to obtain a reference working condition characteristic sequence for the electric wheel dump truck.

4. The method for predicting the energy consumption of electric wheel dump trucks based on historical operating conditions as described in claim 3, characterized in that, The step of fitting the nonlinear scaling path of the operating condition feature sequence to the historical operating condition feature sequence set to obtain the time-series mapping path of the electric wheel dump truck includes: Using the operating condition feature sequence as a reference template and the historical operating condition feature sequence in the set of historical operating condition feature sequences to be matched as test samples, the cost matrix of the electric wheel dump truck is constructed. The cumulative cost matrix of the electric wheel dump truck is obtained by planning and pathfinding on the cost matrix. The curved path of the electric wheel dump truck is obtained by backtracking from the direction of minimum cumulative cost in the cumulative cost matrix. The feature point indexes in the curved path are paired and encoded with the historical working condition feature sequence to obtain the time-series mapping path of the electric wheel dump truck.

5. The method for predicting the energy consumption of electric wheel dump trucks based on historical operating conditions as described in claim 1, characterized in that, The formula for calculating the weighted correction coefficient is as follows: ； In the formula, The weighted correction coefficient is... The preset baseline energy consumption confidence coefficient, For the time-series mapping path, the first Normalized deviation of each mapping node This is the path length factor of the time-series mapping path. The preset time decay factor, Let be the standard deviation of the local vehicle speed deviation. This is the average of the local vehicle speed deviations. It is a natural constant. The index number of the node in the time-series mapping path.

6. The method for predicting the energy consumption of electric wheel dump trucks based on historical operating conditions as described in claim 1, characterized in that, The method of jointly indexing the historical energy consumption records based on the slope label and the load mass signal of the electric wheel dump truck to obtain the basic energy consumption value of the electric wheel dump truck includes: Extract the load mass value from the load mass signal of the electric wheel dump truck to obtain the load characteristic value of the electric wheel dump truck; Based on the slope level coding of the slope label, the historical working condition feature database is anchored to obtain the historical energy consumption record storage partition of the electric wheel dump truck. Using the load characteristic value as the index key, a key-value search is performed on the historical energy consumption record storage partition to obtain the candidate energy consumption record set of the electric wheel dump truck; The energy consumption values ​​in the candidate energy consumption record set are fused to obtain the basic energy consumption value of the electric wheel dump truck.

7. The method for predicting the energy consumption of electric wheel dump trucks based on historical operating conditions as described in claim 1, characterized in that, The step of scaling the base energy consumption value based on the actual energy consumption benchmark to obtain the predicted total energy consumption of the electric wheel dump truck includes: Historical energy consumption records associated with the reference operating condition feature sequence are extracted from the historical operating condition feature database to obtain the benchmark energy consumption reference value of the electric wheel dump truck. The scaling factor of the electric wheel dump truck is obtained by calculating the ratio between the actual energy consumption benchmark value and the benchmark energy consumption reference value. Based on the scaling factor, the base energy consumption value is weighted and adjusted to obtain the predicted energy consumption component of the electric wheel dump truck. The predicted energy consumption components are accumulated and aggregated to obtain the total predicted energy consumption of the electric wheel dump truck.

8. An energy consumption prediction system for electric wheel dump trucks based on historical operating conditions, characterized in that, The system for implementing the energy consumption prediction method for electric wheel dump trucks based on historical operating conditions as described in claim 1 includes: The feature serialization module is used to serialize and arrange the working condition feature points of the original operating parameter stream of the electric wheel dump truck based on the running time sequence of the electric wheel dump truck, so as to obtain the working condition feature sequence of the electric wheel dump truck. The time-series matching library module is used to perform time-series normalization matching between the working condition feature sequence and the historical working condition feature sequence in the historical working condition feature library of the electric wheel dump truck to obtain the reference working condition feature sequence of the electric wheel dump truck. The energy consumption benchmark correction module is used to perform point-by-point deviation analysis on the vehicle speed values ​​at corresponding time positions in the operating condition feature sequence and the reference operating condition feature sequence, and to perform weighted correction on the historical energy consumption records in the historical operating condition feature database based on the accumulated deviation obtained from the analysis, so as to obtain the actual energy consumption benchmark value of the electric wheel dump truck. Specifically, it is used for: The vehicle speed values ​​at the same mapping node in the working condition feature sequence and the reference working condition feature sequence are extracted synchronously to obtain the real-time vehicle speed sample value and the historical vehicle speed sample value of the electric wheel dump truck. The local speed deviation of the electric wheel dump truck is obtained by comparing the real-time vehicle speed sample value with the historical vehicle speed sample value. Based on the time-series mapping path of the electric wheel dump truck, the local speed deviation is accumulated and aggregated to obtain the cumulative deviation of the electric wheel dump truck. Based on the accumulated deviation, the preset deviation-coefficient mapping table is checked and matched to obtain the weighted correction coefficient of the electric wheel dump truck. Historical energy consumption records matching the reference operating condition feature sequence are extracted from the historical operating condition feature database and used as the baseline energy consumption original value of the electric wheel dump truck. Based on the weighted correction coefficient, the original value of the benchmark energy consumption is adjusted by weighting to obtain the actual energy consumption benchmark value of the electric wheel dump truck. The road slope labeling module is used to divide the forward path of the electric wheel dump truck into continuous road segment segments based on abrupt changes in slope values ​​in a preset slope map and in conjunction with the actual energy consumption benchmark value, thereby obtaining the slope label of the electric wheel dump truck. Specifically, it is used for: By performing differential comparisons on the slope values ​​of the preset slope map, the set of slope abrupt change points of the electric wheel dump truck is obtained. Based on the deviation between the actual energy consumption benchmark value and the average energy consumption of the same period in the historical working condition feature library, a significance test is performed on the slope change point set to obtain the key slope change point sequence of the electric wheel dump truck. Using the sequence of key slope jump points as the road segmentation boundary, the forward path of the electric wheel dump truck is divided into road segments to obtain the main control slope feature value of the electric wheel dump truck. The main control slope feature value is graded to obtain the slope label of the electric wheel dump truck; The basic energy consumption index module is used to perform a joint indexing of the historical energy consumption record values ​​based on the slope label and the load mass signal of the electric wheel dump truck, so as to obtain the basic energy consumption value of the electric wheel dump truck. The total energy consumption prediction module is used to scale the base energy consumption value based on the actual energy consumption benchmark value to obtain the predicted total energy consumption of the electric wheel dump truck.

Images