An engineering machinery intelligent scheduling method and system based on vehicle-mounted OBD data

Abstract

The present application relates to a kind of engineering machinery intelligent scheduling method and system based on vehicle OBD data, belong to engineering machinery and intelligent construction technical field.Wherein, the method includes: through the vehicle-mounted Internet of Things box deployed in vehicle, from OBD-II interface real-time recording engine operating condition capture engineering machinery operation dynamic, identify the characteristic curve of engine under different operating conditions;Through engine operating condition detection method, identify engineering machinery information, engine operating condition, driver information, order information and order data are fused, and efficiency and cost index chart are generated;Through dynamic data flow analysis technology, identify engine operating condition state, output the highest work efficiency engineering machinery equipment and operator configuration in this order, and generate intelligent scheduling strategy;According to the best engineering machinery equipment driver allocation chart, analyze the parameters of engineering machinery type and engine operating condition, and distribute the best driver and the highest efficiency engineering machinery.

Description

Technical Field

[0001] This invention belongs to the field of engineering machinery and intelligent construction technology, specifically relating to an intelligent scheduling method and system for engineering machinery based on vehicle-mounted OBD data. Background Technology

[0002] With the widespread application of construction machinery in building, mining, and infrastructure construction, the efficient operation and rational scheduling of machinery have become crucial for improving construction efficiency and reducing costs. Traditional construction machinery scheduling mainly relies on manual experience or static scheduling methods, which suffers from problems such as unreasonable order allocation, low equipment utilization, energy waste, and safety hazards. Furthermore, significant differences in driver skill levels and work habits also have a substantial impact on construction efficiency and machinery wear and tear. In recent years, with the development of vehicle-mounted Internet of Things (IoT) technology, construction machinery is generally equipped with OBD-II interfaces and various sensors, enabling real-time collection of data such as engine status, hydraulic pressure, fuel consumption, battery voltage, and machinery workload, providing a data foundation for intelligent scheduling. However, most current scheduling methods only utilize single-source engine operating condition data, lacking multi-dimensional fusion analysis of driver behavior, environmental conditions, and machinery status. This makes it difficult to comprehensively assess order efficiency and cost, and even more difficult to dynamically adapt to the complex changes at the construction site. Therefore, there is an urgent need for an intelligent scheduling method based on multi-source data fusion and dynamic analysis to achieve optimal allocation of construction machinery and drivers, improve construction efficiency, reduce operating costs, and ensure operational safety. Summary of the Invention

[0003] To address the aforementioned problems in the existing technology, this invention provides an intelligent scheduling method for engineering machinery based on onboard OBD data.

[0004] The objective of this invention can be achieved through the following technical solutions:

[0005] S1: Through the vehicle-mounted IoT box deployed in the vehicle, the engine operating conditions are recorded in real time from the OBD-II interface to capture the dynamic operation of the construction machinery, and the operating status is detected based on sensor data. The raw engine operating condition data during the operation of the construction machinery is collected in real time based on the sensor interface.

[0006] S2: Based on the collected engine operating condition data, identify the construction machinery information through the engine operating condition detection method, analyze the engine operating condition of the target area according to the construction rules, and fuse the engine operating condition, driver information, order information and order data through a multi-source fusion algorithm. Input the multi-source fusion data into the engineering cost model to generate an efficiency / cost index chart of the construction machinery and drivers required to undertake this order.

[0007] S3: Identify the construction machinery and operators with the best work efficiency and lowest cost in historical orders through dynamic data stream analysis technology. Input the construction machinery information and driver information into the multimodal fusion model to output the construction machinery equipment and operator configuration with the highest work efficiency in the current work order, and generate an intelligent scheduling strategy.

[0008] The method for identifying historical orders using the dynamic data stream analysis technology is as follows:

[0009] Establish a historical order data stream database, which includes engine operating condition characteristic parameters, driver working status parameters and mechanical operating performance indicators collected from previous construction orders;

[0010] The historical order data stream is segmented using a sliding window, and the characteristic factors affecting order efficiency and cost are identified through correlation analysis and causal inference; and pattern recognition is performed on the segmented data stream based on a time series clustering algorithm.

[0011] Based on the data stream after pattern recognition, calculate the efficiency and cost values ​​of different historical orders under different engine operating conditions; and extract the engineering machinery and driver information corresponding to the optimal efficiency and lowest cost based on the calculation results.

[0012] The criteria for generating the intelligent scheduling strategy are as follows:

[0013] Based on the efficiency / cost index chart, the efficiency and cost values ​​of idle construction machinery and drivers are ranked, and the combination with the highest efficiency and lowest cost is selected first. When there is a conflict between efficiency and cost, a weighted scoring mechanism is used to comprehensively calculate the optimal allocation scheme.

[0014] Based on the engine operating conditions of the order, the suitability of candidate construction machinery is verified, and the best-performing machinery under the same historical engine operating conditions is selected; the fatigue, health status and operating habits of the drivers are assessed, and candidate drivers with safety risks are eliminated; and under the premise of meeting the suitability verification, the drivers and construction machinery with the best scheduling efficiency are dispatched.

[0015] S4: Analyze the parameters of the type of construction machinery and engine operating conditions according to the intelligent scheduling strategy, record abnormal information in the scheduling process, and when a new rental order is received, distribute the order to the combination of driver and construction machinery with the best efficiency or cost by identifying the status of equipment and personnel in the available domain.

[0016] Specifically, the method for capturing the dynamic operation of construction machinery is as follows: during the operation of construction machinery, sensor data signals are sampled in real time to obtain engine operating condition information at the work location; the sampled signals are adjusted to observe changes in the operating status of construction machinery and obtain the dynamic operation of construction machinery.

[0017] Specifically, the method for generating the efficiency / cost indicator chart is as follows:

[0018] The collected engine operating condition data, driver information, order information, and order data are analyzed to generate engine operating condition characteristic parameters, driver working status parameters, and mechanical operating performance indicators. The engine operating condition characteristic parameters include construction environment and working conditions information; the driver working status parameters include driver operating status and physical condition information; and the mechanical operating performance indicators include the operating efficiency and energy consumption level information of the construction machinery.

[0019] The engine operating condition characteristic parameters, driver working status parameters, and mechanical operating performance indicators are input into the efficiency cost model to calculate the efficiency cost information of the construction machinery in the target order, and an efficiency / cost index chart that quantitatively represents the efficiency and cost of the construction machinery and the driver is generated based on the efficiency cost information.

[0020] Specifically, the method for fusing data using the multi-source fusion algorithm is as follows: normalizing the engine operating condition characteristic parameters, driver working state parameters, and mechanical operating performance indicators; synchronizing different source data according to timestamps using time series alignment; and assigning weights to the normalized parameters according to a feature weighting method to generate an efficiency cost dataset for inputting into the efficiency cost model.

[0021] Specifically, the multi-source data introduces a multimodal feature encoding mechanism to construct an event time difference vector for the time-series event data and then concatenates the processed feature vectors to generate a high-dimensional fusion feature input vector.

[0022] Specifically, the implementation process of the in-vehicle IoT box includes:

[0023] By connecting to the vehicle controller local area network bus interface via the OBD mainline, the underlying operating data of the construction machinery can be analyzed and collected in real time.

[0024] The embedded edge computing unit performs edge preprocessing on the underlying running data, including identifying and removing instantaneous outliers and null values ​​using a sliding window algorithm; incrementally compressing and encoding the data and packaging it into standard frames; and managing key indicator data and unuploaded cached data in a circular queue through a local caching mechanism.

[0025] The integrated communication module enables a two-way encrypted connection with the cloud-based analytics platform, allowing the processed, standardized, multi-dimensional vehicle condition data to be uploaded in an event-triggered manner.

[0026] Specifically, the method for detecting the engine operating condition is as follows:

[0027] The engine speed, torque, fuel consumption rate, coolant temperature, braking status and transmission system status are collected in real time through the OBD-II interface. Based on the geological characteristics of the construction site and the road surface friction coefficient, the operation intensity, energy consumption level and operational stability of the construction machinery are identified. Through a multi-source data fusion method, the engine operating conditions are combined with the environmental operating conditions to generate the engine operating condition characteristics of the construction machinery during the scheduling process.

[0028] Specifically, an intelligent scheduling system for construction machinery based on onboard OBD data, used to execute any one of the methods described in claims 1-7, characterized in that it includes:

[0029] Data Acquisition and Scheduling Module: Through the vehicle-mounted IoT box deployed in the vehicle, the engine operating conditions are recorded in real time from the OBD-II interface to capture the dynamic operation of the construction machinery, and the operating status is detected based on sensor data. Based on the sensor interface, the raw engine operating condition data during the operation of the construction machinery is collected in real time.

[0030] Operating condition verification module: Based on the collected engine operating condition data, the module identifies the construction machinery information through engine operating condition detection methods, analyzes the engine operating condition of the target area according to construction rules, and integrates engine operating condition, driver information, order information and order data through a multi-source fusion algorithm. The multi-source fusion data is then input into the engineering cost model to generate an efficiency / cost index chart of the construction machinery and drivers required to undertake this order.

[0031] Data Analysis Module: Through dynamic data stream analysis technology, identify the construction machinery and operators with the best work efficiency and lowest cost in historical orders. Input the construction machinery information and driver information into a multimodal fusion model to output the construction machinery equipment and operator configuration with the highest work efficiency in the current work order, and generate an intelligent scheduling strategy.

[0032] The method for identifying historical orders using the dynamic data stream analysis technology is as follows:

[0033] Establish a historical order data stream database, which includes engine operating condition characteristic parameters, driver working status parameters and mechanical operating performance indicators collected from previous construction orders;

[0034] The historical order data stream is segmented using a sliding window, and the characteristic factors affecting order efficiency and cost are identified through correlation analysis and causal inference; and pattern recognition is performed on the segmented data stream based on a time series clustering algorithm.

[0035] Based on the data stream after pattern recognition, calculate the efficiency and cost values ​​of different historical orders under different engine operating conditions; and extract the engineering machinery and driver information corresponding to the optimal efficiency and lowest cost based on the calculation results.

[0036] The criteria for generating the intelligent scheduling strategy are as follows:

[0037] Based on the efficiency / cost index chart, the efficiency and cost values ​​of idle construction machinery and drivers are ranked, and the combination with the highest efficiency and lowest cost is selected first. When there is a conflict between efficiency and cost, a weighted scoring mechanism is used to comprehensively calculate the optimal allocation scheme.

[0038] Based on the engine operating conditions of the order, the suitability of candidate construction machinery is verified, and the best-performing machinery under the same historical engine operating conditions is selected; the fatigue, health status and operating habits of the drivers are assessed, and candidate drivers with safety risks are eliminated; and under the premise of meeting the suitability verification, the drivers and construction machinery with the best scheduling efficiency are dispatched.

[0039] Anomaly identification module: Based on the intelligent scheduling strategy, it analyzes the parameters of the type of construction machinery and the engine operating condition, records the abnormal information in the scheduling process, and when a new rental order is received, it identifies the status of equipment and personnel in the available domain and distributes the order to the combination of driver and construction machinery with the best efficiency or cost.

[0040] The beneficial effects of this invention are as follows:

[0041] This invention deploys an onboard IoT box on construction machinery to collect real-time data from the OBD-II interface and sensors, enabling multi-source dynamic monitoring of machinery operation status, driver behavior, and the construction environment. It utilizes multi-source fusion algorithms, efficiency-cost models, and dynamic data stream analysis technology to intelligently analyze historical order data, thereby identifying the optimal combination of machinery and drivers with the highest work efficiency and lowest cost. Based on this, the invention can automatically generate the best machinery and driver allocation scheme for the target engine operating condition area, achieving intelligent scheduling of construction orders. Compared with existing technologies, this invention has the following advantages: Firstly, it improves the utilization rate and operating efficiency of construction machinery, and reduces energy consumption and operating costs through optimized allocation using historical data. Secondly, by combining driver status and machinery suitability assessment, it effectively reduces safety risks and equipment failure rates. Furthermore, dynamic noise separation and real-time engine condition monitoring enhance the reliability and adaptability of the scheduling scheme, enabling machinery scheduling to flexibly respond to changes in the construction environment and temporary rental orders. In summary, this invention provides an efficient, intelligent, safe, and cost-controllable method for scheduling construction machinery, with significant engineering application value and promising prospects for widespread application. Attached Figure Description

[0042] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0043] Figure 1This is a flowchart illustrating an intelligent scheduling method and system for engineering machinery based on vehicle-mounted OBD data, according to the present invention. Detailed Implementation

[0044] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided.

[0045] Please see Figure 1 A method for intelligent scheduling of construction machinery based on onboard OBD data:

[0046] S1: Through the vehicle-mounted IoT box deployed in the vehicle, the engine operating conditions are recorded in real time from the OBD-II interface to capture the dynamic operation of the construction machinery, and the operating status is detected based on sensor data. The raw engine operating condition data during the operation of the construction machinery is collected in real time based on the sensor interface.

[0047] S2: Based on the collected engine operating condition data, identify the construction machinery information through the engine operating condition detection method, analyze the engine operating condition of the target area according to the construction rules, and fuse the engine operating condition, driver information, order information and order data through a multi-source fusion algorithm. Input the multi-source fusion data into the engineering cost model to generate an efficiency / cost index chart of the construction machinery and drivers required to undertake this order.

[0048] S3: Identify the construction machinery and operators with the best work efficiency and lowest cost in historical orders through dynamic data stream analysis technology. Input the construction machinery information and driver information into the multimodal fusion model to output the construction machinery equipment and operator configuration with the highest work efficiency in the current work order, and generate an intelligent scheduling strategy.

[0049] The method for identifying historical orders using the dynamic data stream analysis technology is as follows:

[0050] Establish a historical order data stream database, which includes engine operating condition characteristic parameters, driver working status parameters and mechanical operating performance indicators collected from previous construction orders;

[0051] The historical order data stream is segmented using a sliding window, and the characteristic factors affecting order efficiency and cost are identified through correlation analysis and causal inference; and pattern recognition is performed on the segmented data stream based on a time series clustering algorithm.

[0052] Based on the data stream after pattern recognition, calculate the efficiency and cost values ​​of different historical orders under different engine operating conditions; and extract the engineering machinery and driver information corresponding to the optimal efficiency and lowest cost based on the calculation results.

[0053] The criteria for generating the intelligent scheduling strategy are as follows:

[0054] Based on the efficiency / cost index chart, the efficiency and cost values ​​of idle construction machinery and drivers are ranked, and the combination with the highest efficiency and lowest cost is selected first. When there is a conflict between efficiency and cost, a weighted scoring mechanism is used to comprehensively calculate the optimal allocation scheme.

[0055] Based on the engine operating conditions of the order, the suitability of candidate construction machinery is verified, and the best-performing machinery under the same historical engine operating conditions is selected; the fatigue, health status and operating habits of the drivers are assessed, and candidate drivers with safety risks are eliminated; and under the premise of meeting the suitability verification, the drivers and construction machinery with the best scheduling efficiency are dispatched.

[0056] S4: Analyze the parameters of the type of construction machinery and engine operating conditions according to the intelligent scheduling strategy, record abnormal information in the scheduling process, and when a new rental order is received, distribute the order to the combination of driver and construction machinery with the best efficiency or cost by identifying the status of equipment and personnel in the available domain.

[0057] Specifically, the method for capturing the dynamic operation of construction machinery is as follows: during the operation of construction machinery, sensor data signals are sampled in real time to obtain engine operating condition information at the work location; the sampled signals are adjusted to observe changes in the operating status of construction machinery and obtain the dynamic operation of construction machinery.

[0058] Specifically, the method for generating the efficiency / cost indicator chart is as follows:

[0059] The collected engine operating condition data, driver information, order information, and order data are analyzed to generate engine operating condition characteristic parameters, driver working status parameters, and mechanical operating performance indicators. The engine operating condition characteristic parameters include construction environment and working conditions information; the driver working status parameters include driver operating status and physical condition information; and the mechanical operating performance indicators include the operating efficiency and energy consumption level information of the construction machinery.

[0060] The engine operating condition characteristic parameters, driver working status parameters, and mechanical operating performance indicators are input into the efficiency cost model to calculate the efficiency cost information of the construction machinery in the target order, and an efficiency / cost index chart that quantitatively represents the efficiency and cost of the construction machinery and the driver is generated based on the efficiency cost information.

[0061] Specifically, the method for fusing data using the multi-source fusion algorithm is as follows: normalizing the engine operating condition characteristic parameters, driver working state parameters, and mechanical operating performance indicators; synchronizing different source data according to timestamps using time series alignment; and assigning weights to the normalized parameters according to a feature weighting method to generate an efficiency cost dataset for inputting into the efficiency cost model.

[0062] In the temporary construction scheduling example, vehicle-mounted IoT boxes are deployed on all excavators and dump trucks to collect real-time mechanical operation data such as engine speed, hydraulic pressure, fuel consumption, and mechanical load through the OBD-II interface and sensors. At the same time, driver heart rate, operation frequency, and driving habits data are collected, and environmental data such as terrain slope, soil moisture, and wind speed in the construction area are recorded.

[0063] The collected data is normalized and then aligned with time series data before being input into a multi-source fusion algorithm. This algorithm integrates information on mechanical performance, driver status, and environmental conditions to generate an efficiency / cost index chart for engineering orders. Historical order data is analyzed using dynamic data stream technology to identify the optimal combination of machinery and driver, and combined with a dynamic noise separation algorithm to filter out abnormal interference.

[0064] Based on the generated intelligent scheduling strategy, the system automatically allocates the most efficient excavators and dump trucks, and matches them with drivers, achieving intelligent scheduling of earthwork excavation and transportation. Results show that compared to traditional manual scheduling, operational efficiency is increased by approximately 15%, fuel consumption is reduced by approximately 10%, and the risks of driver fatigue and mechanical failure are significantly decreased.

[0065] Specifically, the multi-source data introduces a multimodal feature encoding mechanism to construct an event time difference vector for the time-series event data and then concatenates the processed feature vectors to generate a high-dimensional fusion feature input vector. The specific calculation formula is as follows:

[0066] ,

[0067] Where s is the weighted fusion of global features, T is the total length of the time window, and h t Let be the hidden state vector at the t-th event step, Wa be the attention weight matrix, ba be the attention bias vector, and u be the hidden state vector at the t-th event step. t Let v be the intermediate representation vector, and v be the attention score vector.

[0068] Specifically, the implementation process of the in-vehicle IoT box includes:

[0069] By connecting to the vehicle controller local area network bus interface via the OBD mainline, the underlying operating data of the construction machinery can be analyzed and collected in real time.

[0070] The embedded edge computing unit performs edge preprocessing on the underlying running data, including identifying and removing instantaneous outliers and null values ​​using a sliding window algorithm; incrementally compressing and encoding the data and packaging it into standard frames; and managing key indicator data and unuploaded cached data in a circular queue through a local caching mechanism.

[0071] The integrated communication module enables a two-way encrypted connection with the cloud-based analytics platform, allowing the processed, standardized, multi-dimensional vehicle condition data to be uploaded in an event-triggered manner.

[0072] Specifically, the method for detecting the engine operating condition is as follows:

[0073] The engine speed, torque, fuel consumption rate, coolant temperature, braking status and transmission system status are collected in real time through the OBD-II interface. Based on the geological characteristics of the construction site and the road surface friction coefficient, the operation intensity, energy consumption level and operational stability of the construction machinery are identified. Through a multi-source data fusion method, the engine operating conditions are combined with the environmental operating conditions to generate the engine operating condition characteristics of the construction machinery during the scheduling process.

[0074] In the rental order example, by identifying the type, operating status, and availability of the rented machinery, and simultaneously collecting driver operating habits and environmental condition parameters, the collected information is input into a multimodal fusion model. This model is then combined with historical order efficiency and cost data to generate efficiency and cost indicator charts. Dynamic data stream analysis technology identifies historically optimal combinations and optimizes allocation based on constraints (order duration, machinery availability, driver scheduling, and equipment maintenance status). Finally, the system generates the optimal machinery and driver allocation scheme and outputs an intelligent scheduling strategy for on-site operational guidance. Experimental results show that using this method to complete orders increases machinery utilization by approximately 20%, shortens construction time by approximately 12%, and effectively reduces machinery wear and tear and driver operational risks, ensuring efficient and safe completion of temporary construction orders.

[0075] Specifically, an intelligent scheduling system for construction machinery based on onboard OBD data, used to execute any one of the methods described in claims 1-7, characterized in that it includes:

[0076] Data Acquisition and Scheduling Module: Through the vehicle-mounted IoT box deployed in the vehicle, the engine operating conditions are recorded in real time from the OBD-II interface to capture the dynamic operation of the construction machinery, and the operating status is detected based on sensor data. Based on the sensor interface, the raw engine operating condition data during the operation of the construction machinery is collected in real time.

[0077] Operating condition verification module: Based on the collected engine operating condition data, the module identifies the construction machinery information through engine operating condition detection methods, analyzes the engine operating condition of the target area according to construction rules, and integrates engine operating condition, driver information, order information and order data through a multi-source fusion algorithm. The multi-source fusion data is then input into the engineering cost model to generate an efficiency / cost index chart of the construction machinery and drivers required to undertake this order.

[0078] Data Analysis Module: Through dynamic data stream analysis technology, identify the construction machinery and operators with the best work efficiency and lowest cost in historical orders. Input the construction machinery information and driver information into a multimodal fusion model to output the construction machinery equipment and operator configuration with the highest work efficiency in the current work order, and generate an intelligent scheduling strategy.

[0079] The method for identifying historical orders using the dynamic data stream analysis technology is as follows:

[0080] Establish a historical order data stream database, which includes engine operating condition characteristic parameters, driver working status parameters and mechanical operating performance indicators collected from previous construction orders;

[0081] The historical order data stream is segmented using a sliding window, and the characteristic factors affecting order efficiency and cost are identified through correlation analysis and causal inference; and pattern recognition is performed on the segmented data stream based on a time series clustering algorithm.

[0082] Based on the data stream after pattern recognition, calculate the efficiency and cost values ​​of different historical orders under different engine operating conditions; and extract the engineering machinery and driver information corresponding to the optimal efficiency and lowest cost based on the calculation results.

[0083] The criteria for generating the intelligent scheduling strategy are as follows:

[0084] Based on the efficiency / cost index chart, the efficiency and cost values ​​of idle construction machinery and drivers are ranked, and the combination with the highest efficiency and lowest cost is selected first. When there is a conflict between efficiency and cost, a weighted scoring mechanism is used to comprehensively calculate the optimal allocation scheme.

[0085] Based on the engine operating conditions of the order, the suitability of candidate construction machinery is verified, and the best-performing machinery under the same historical engine operating conditions is selected; the fatigue, health status and operating habits of the drivers are assessed, and candidate drivers with safety risks are eliminated; and under the premise of meeting the suitability verification, the drivers and construction machinery with the best scheduling efficiency are dispatched.

[0086] Anomaly identification module: Based on the intelligent scheduling strategy, it analyzes the parameters of the type of construction machinery and the engine operating condition, records the abnormal information in the scheduling process, and when a new rental order is received, it identifies the status of equipment and personnel in the available domain and distributes the order to the combination of driver and construction machinery with the best efficiency or cost.

[0087] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for intelligent scheduling of construction machinery based on onboard OBD data, characterized in that, include: S1: Through the vehicle-mounted IoT box deployed in the vehicle, the engine operating conditions are recorded in real time from the OBD-II interface to capture the dynamic operation of the construction machinery, and the operating status is detected based on sensor data. The raw engine operating condition data during the operation of the construction machinery is collected in real time based on the sensor interface. S2: Based on the collected engine operating condition data, identify the construction machinery information through the engine operating condition detection method, analyze the engine operating condition of the target area according to the construction rules, and fuse the engine operating condition, driver information, order information and order data through a multi-source fusion algorithm. Input the multi-source fusion data into the engineering cost model to generate an efficiency / cost index chart of the construction machinery and drivers required to undertake this order. S3: Identify the construction machinery and operators with the best work efficiency and lowest cost in historical orders through dynamic data stream analysis technology. Input the construction machinery information and driver information into the multimodal fusion model to output the construction machinery equipment and operator configuration with the highest work efficiency in the current work order, and generate an intelligent scheduling strategy. The method for identifying historical orders using the dynamic data stream analysis technology is as follows: Establish a historical order data stream database, which includes engine operating condition characteristic parameters, driver working status parameters and mechanical operating performance indicators collected from previous construction orders; The historical order data stream is segmented using a sliding window, and the characteristic factors affecting order efficiency and cost are identified through correlation analysis and causal reasoning. The segmented data stream is then subjected to pattern recognition based on a time series clustering algorithm. Based on the data stream after pattern recognition, calculate the efficiency and cost values ​​of different historical orders under different engine operating conditions; Based on the calculation results, information on the construction machinery and drivers corresponding to the optimal efficiency and lowest cost is extracted. The criteria for generating the intelligent scheduling strategy are as follows: Based on the efficiency / cost index chart, the efficiency and cost values ​​of idle construction machinery and drivers are ranked, and the combination with the highest efficiency and lowest cost is selected first. When there is a conflict between efficiency and cost, a weighted scoring mechanism is used to comprehensively calculate the optimal allocation scheme. Based on the engine operating conditions of the order, the suitability of candidate construction machinery is verified, and the best-performing machinery under the same historical engine operating conditions is selected; the fatigue, health status and operating habits of the drivers are assessed, and candidate drivers with safety risks are eliminated; and under the premise of meeting the suitability verification, the drivers and construction machinery with the best scheduling efficiency are dispatched. S4: Analyze the parameters of the type of construction machinery and engine operating conditions according to the intelligent scheduling strategy, record abnormal information in the scheduling process, and when a new rental order is received, distribute the order to the combination of driver and construction machinery with the best efficiency or cost by identifying the status of equipment and personnel in the available domain.

2. The method according to claim 1, characterized in that, The method for capturing the dynamic operation of construction machinery is as follows: during the operation of construction machinery, sensor data signals are sampled in real time to obtain engine operating information at the work location; the sampled signals are adjusted to observe changes in the operating status of construction machinery and obtain the dynamic operation of construction machinery.

3. The method according to claim 1, characterized in that, The method for generating the efficiency / cost index chart is as follows: The collected engine operating condition data, driver information, order information, and order data are analyzed to generate engine operating condition characteristic parameters, driver working status parameters, and mechanical operating performance indicators. The engine operating condition characteristic parameters include construction environment and working conditions information; the driver working status parameters include driver operating status and physical condition information; and the mechanical operating performance indicators include the operating efficiency and energy consumption level information of the construction machinery. The engine operating condition characteristic parameters, driver working status parameters, and mechanical operating performance indicators are input into the efficiency cost model to calculate the efficiency cost information of the construction machinery in the target order, and an efficiency / cost index chart that quantitatively represents the efficiency and cost of the construction machinery and the driver is generated based on the efficiency cost information.

4. The method according to claim 3, characterized in that, The method for fusing data using the multi-source fusion algorithm is as follows: normalize the engine operating condition characteristic parameters, driver working status parameters, and mechanical operating performance indicators. Synchronize different source data by timestamp using time series alignment; The normalized parameters are weighted according to the feature weighting method to generate an efficiency cost dataset for input into the efficiency cost model.

5. The method according to claim 1, characterized in that, The implementation process of the in-vehicle IoT box includes: By connecting to the vehicle controller local area network bus interface via the OBD mainline, the underlying operating data of the construction machinery can be analyzed and collected in real time. The embedded edge computing unit performs edge preprocessing on the underlying running data, including identifying and removing instantaneous outliers and null values ​​using a sliding window algorithm; incrementally compressing and encoding the data and packaging it into standard frames; and managing key indicator data and unuploaded cached data in a circular queue through a local caching mechanism. The integrated communication module enables a two-way encrypted connection with the cloud-based analytics platform, allowing the processed, standardized, multi-dimensional vehicle condition data to be uploaded in an event-triggered manner.

6. The method according to claim 4, characterized in that, The multi-source fusion data introduces a multimodal feature encoding mechanism, constructs an event time difference vector for time-series event data, and concatenates the processed feature vectors to generate a high-dimensional fusion feature input vector.

7. The method according to claim 4, characterized in that, The method for detecting the engine operating condition is as follows: The engine speed, torque, fuel consumption rate, coolant temperature, braking status and transmission system status are collected in real time through the OBD-II interface. Based on the geological characteristics of the construction site and the road surface friction coefficient, the operation intensity, energy consumption level and operational stability of the construction machinery are identified. Through a multi-source data fusion method, the engine operating conditions are combined with the environmental operating conditions to generate the engine operating condition characteristics of the construction machinery during the scheduling process.

8. A smart scheduling system for construction machinery based on onboard OBD data, used to execute any one of the methods described in claims 1-7, characterized in that, include: Data Acquisition and Scheduling Module: Through the vehicle-mounted IoT box deployed in the vehicle, the engine operating conditions are recorded in real time from the OBD-II interface to capture the dynamic operation of the construction machinery, and the operating status is detected based on sensor data. Based on the sensor interface, the raw engine operating condition data during the operation of the construction machinery is collected in real time. Operating condition verification module: Based on the collected engine operating condition data, the module identifies the construction machinery information through engine operating condition detection methods, analyzes the engine operating condition of the target area according to construction rules, and integrates engine operating condition, driver information, order information and order data through a multi-source fusion algorithm. The multi-source fusion data is then input into the engineering cost model to generate an efficiency / cost index chart of the construction machinery and drivers required to undertake this order. Data Analysis Module: Through dynamic data stream analysis technology, identify the construction machinery and operators with the best work efficiency and lowest cost in historical orders. Input the construction machinery information and driver information into a multimodal fusion model to output the construction machinery equipment and operator configuration with the highest work efficiency in the current work order, and generate an intelligent scheduling strategy. The method for identifying historical orders using the dynamic data stream analysis technology is as follows: Establish a historical order data stream database, which includes engine operating condition characteristic parameters, driver working status parameters and mechanical operating performance indicators collected from previous construction orders; The historical order data stream is segmented using a sliding window, and the characteristic factors affecting order efficiency and cost are identified through correlation analysis and causal reasoning. The segmented data stream is then subjected to pattern recognition based on a time series clustering algorithm. Based on the data stream after pattern recognition, calculate the efficiency and cost values ​​of different historical orders under different engine operating conditions; Based on the calculation results, information on the construction machinery and drivers corresponding to the optimal efficiency and lowest cost is extracted. The criteria for generating the intelligent scheduling strategy are as follows: Based on the efficiency / cost index chart, the efficiency and cost values ​​of idle construction machinery and drivers are ranked, and the combination with the highest efficiency and lowest cost is selected first. When there is a conflict between efficiency and cost, a weighted scoring mechanism is used to comprehensively calculate the optimal allocation scheme. Based on the engine operating conditions of the order, the suitability of candidate construction machinery is verified, and the best-performing machinery under the same historical engine operating conditions is selected; the fatigue, health status and operating habits of the drivers are assessed, and candidate drivers with safety risks are eliminated; and under the premise of meeting the suitability verification, the drivers and construction machinery with the best scheduling efficiency are dispatched. Anomaly identification module: Based on the intelligent scheduling strategy, it analyzes the parameters of the type of construction machinery and the engine operating condition, records the abnormal information in the scheduling process, and when a new rental order is received, it identifies the status of equipment and personnel in the available domain and distributes the order to the combination of driver and construction machinery with the best efficiency or cost.

Images