Against the backdrop of precision agriculture and the development of intelligent agricultural machinery, current domestic monitoring systems for wheat combine harvesters are plagued by limited functionality, low intelligence, significant errors in parameter monitoring, and yield estimation results prone to inaccuracies. Specifically, they lag behind mature international systems in terms of fault warning accuracy, data transmission efficiency, and yield visualization capabilities. This study seeks to realize comprehensive and precise monitoring, reliable fault early warning, and intelligent yield prediction for wheat combine harvesters across all operating conditions. To this end, it innovatively adopts CAN bus integration technology and impulse-type grain flow sensors to develop a comprehensive system for monitoring the operational status and warning faults of wheat combine harvesters, which covers the entire operational process. By integrating GPS positioning, multi-sensor parameter acquisition, and intelligent analysis modules through CAN bus integration, the system enables unified monitoring of geographic information, operational data, cleaning loss, and fault status. Additionally, it incorporates a yield measurement module based on an impulse-type grain flow sensor to generate the real-time yield distribution maps. Field experiments demonstrate that the system achieves an alarm accuracy of 97.3%, controls the fuel consumption measurement error within 5%, and limits the relative error of yield measurement accuracy to no more than 4%. Notably, the impulse-type grain flow sensor exhibits stable static detection accuracy and rapid, precise dynamic measurement performance—laying a solid foundation for the automation and intelligent advancement of combine harvester technologies.

The core objective of this study is to address critical challenges in the operational monitoring and fault early warning of wheat combine harvesters. To this end, this study designed a field-oriented multi-parameter detection system for wheat combine harvesters, which utilizes the CAN bus and virtual instrumentation. Key challenges in this field include three aspects: first, manual inspection is inefficient and lacks automated detection methods, making it difficult to meet the real-time requirements of large-scale operations; second, fault early warning accuracy is low, as single-parameter evaluation is prone to false positives and false negatives; third, monitoring parameters function in isolation, leading to significant data inconsistencies that hinder the early detection of potential faults. To address these issues, this study focuses on three key tasks: establishing a multi-parameter collaborative monitoring framework, optimizing hardware and communication protocols, and developing data processing methods for fault detection and warning. Specifically, sensors for fuel consumption, Hall-effect rotational speed, and strain-gauge torque are deployed at critical components of the harvester. The system then efficiently transmits operational status data via the CAN bus to a processing module, enabling remote real-time monitoring of the harvester’s comprehensive operational conditions. For the designed fault warning algorithm, it dynamically adjusts warning thresholds by comparing characteristic parameters with historical data, thereby achieving accurate fault identification and timely warning responses. This study innovatively transmitted multi-source sensor data through the high-anti-interference CAN bus and developed a fault warning algorithm incorporating feature recognition and dynamic thresholds. In simulated experiments, the measurement errors of both instantaneous and cumulative fuel consumption were ≤5%, while the system achieved a warning accuracy of 97.3% and a response time of ≤180 ms. This represents a 15.3-percentage-point improvement in accuracy compared to traditional single-parameter warning systems. Overall, this study addresses the challenge of multi-parameter integrated monitoring for wheat combine harvesters and provides a scalable technical solution for hardware integration and comprehensive data analysis. It also offers a reference for the intelligent upgrading of Chinese harvesters, which is expected to accelerate the transformation of agricultural mechanization toward precision and informatization.

An accurate and rapid detection is highly required for broken or damaged maize kernels in modern agriculture. However, the conventional manual approaches cannot fully meet the large-scale applications in recent years, due to the inherently error-prone tasks, labor-intensity, and time-consuming. Moreover, significant constraints have been posed on the high efficiency and scalability of modern farming. In contrast, image recognition can be expected to substantially enhance the accuracy and efficiency of broken kernel detection using deep learning, such as the SqueezeNet network. Some challenges of the SqueezeNet model still remained in the identification of small targets, such as the maize kernels. In the depth of the network, complex and multi-layered convolutions are better required to effectively process the input images. Since the deeper architectures can enhance feature extraction, substantial computational demands have also been imposed on the processing power, memory, and storage. Particularly, the real-time applications cannot fully meet the resource-constrained environments, such as the mobile devices or embedded systems that are commonly deployed in agricultural settings. In this study, an optimized variant of the SqueezeNet model was introduced to specifically detect the broken maize kernels. The architecture (termed SqueezeNet-dw2) was used to enhance the original SqueezeNet framework. The computational complexity was reduced to improve the efficiency more suitable for real-time agricultural applications. Several key modifications were also introduced into the classic SqueezeNet architecture, in order to enhance the efficiency with less computational complexity. Firstly, the number of fire layers was reduced to the input channels of the final convolutional layer. Additionally, the standard convolutions were replaced with the depthwise separable ones. The feature extraction was preserved to significantly lower the computational costs. Furthermore, the Ghost module was integrated to refine the expanding layer of the Fire module. A 3×3 convolution was also incorporated to effectively reduce the computational demands and the number of parameters. The enhanced architecture was termed SqueezeNet-dw2-gh, indicating the integration of the Ghost module. A more efficient network was obtained after refinement and is better suitable for real-time agricultural applications, compared with the original SqueezeNet. The parametric rectified linear unit (PReLU) was employed as the activation function, in order to adaptively learn the activation parameters during training. The degradation of the accuracy after network simplification was mitigated to maintain high performance with less computational complexity. The final model after optimization was termed SqueezeNet-dw2-gh-P. Experimental results show that the parameter count was reduced to 0.60 MB, a 51.61% decrease compared with the original architecture, while the computational cost was lowered by 48.54%, with a floating point operations of 36.71 MFLOPs. Notably, the optimal network shared the validation and test accuracies of 93.98% and 92.33%, respectively, indicating the effectiveness and efficiency in the accurate detection of the broken maize kernels. In conclusion, the improved SqueezeNet architecture achieved substantial reductions in the parameter count, memory footprint, and computational demands. The suitability of the improved model was obtained for the deployment of resource-constrained mobile and embedded devices. The real-time detection of broken maize kernels can also offer a practical solution in modern agriculture.

Management level and user benefits have greatly contributed to agricultural machinery in recent years. The operational efficiency of agricultural machinery was commonly used to evaluate the utilization rate, operator driving ability, and management efficiency of agricultural machinery. However, the current operational efficiency of agricultural machinery cannot fully represent the overall operational efficiency of agricultural machinery. For example, although the low-power agricultural machinery has low operational efficiency, the generated benefits are not lower than that of high-power agricultural machinery, if the operating time is saturated. In addition, the quality of agricultural machinery operation can seriously affect operational efficiency. Therefore, it is necessary to consider the key influencing factors on the efficiency of agricultural machinery operations. In this study, a comprehensive and comprehensive evaluation was conducted on agricultural machinery operations. The operational efficiency was then evaluated on each agricultural machine using influencing factors. The daily operational information of each machine was taken as a piece of data on that day. The operation status of operators and agricultural machinery were checked to identify the influencing factors on the efficiency of operations, in order to improve the management level and revenue of agricultural machinery. The data was collected from the 32000 deep loosening operations of agricultural machinery. The results show that the main influencing factors on the daily operation efficiency of agricultural machinery were directly obtained, including the daily operation area, fuel consumption, operation quality, repeated operation rate, missed operation rate, and the proportion of effective operation time. The BP_Adaboost neural network (NN) training model was used to evaluate the efficiency of agricultural machinery operation. Manually grading was replaced to avoid the large workload and extremely low efficiency from the subjective factors, inconsistent standards, and labeling errors, due to the large number of agricultural machinery and the large amount of homework data. A comparison was made on the training model and manual grading to predict the remaining data. Manual scoring standards were effectively used to establish the predictive models. A small number of samples were selected to predict the operational efficiency of agricultural machinery. The low accuracy was obtained in the training model if there were too few labeled samples. If the additional labeled samples were added, manual grading was less labor-saving. Semi-supervised BP_Adaboost was utilized to evaluate the efficiency of agricultural machinery operations, where manually scoring some data was marked the daily efficiency. One part was used as training samples, whereas, another part was used as testing samples. The BP_Adaboost was then used to reduce the manual labeling of training samples for the high accuracy of the training model, where the remaining unrated data was predicted after training the model. 1 000 samples were selected from 32 000 deep loosening operation data for labeling, of which 500 were used as training samples and 500 were used as testing samples. The highest prediction accuracy was achieved in the semi-supervised method for the selected experimental data when the probability threshold was 97%. If the threshold was too large, there was only a limited increase in samples; If the sample was too small, misclassified samples led to low accuracy. Therefore, there was a significant impact on the sample selection and termination in semi-supervised methods. The prediction accuracies were achieved in 93.36% and 97.03%, respectively, using the BP_Adaboost, and semi-supervised BP_Adaboost with training samples. Statistical analysis was conducted on 32 000 agricultural machinery operation data from the experiment. The effectiveness of the improved model was obtained by combining the partial power agricultural machinery with different-width machines. The operation efficiency varied greatly in the power agricultural machinery when paired with different width machines. The optimal combination of agricultural machinery was recommended to enhance the operational capabilities, according to the operational efficiency. The accuracy of the improved model was higher than that of using the BP_Adaboost alone, depending largely on the selection of the probability threshold. The generalization and standards can be expected for the different datasets and the optimal thresholds. A more reasonable probability threshold can be selected to assign different weights to various indicators for the better performance of the improved model.

In order to improve the screening performance and cleaning effect of the jujube harvesting machinery cleaning device, a vibrating curved screen device was designed in this study. By analyzing the structure mechanism of the curved sieve body, it was obtained that the arc-shaped mesh hole spacing S was 15-25 mm and the curved mesh hole curvature U was 90°-150°. By exploring the movement state and stress of jujube and impurities on the curved sieve body, it was determined that the horizontal spacing L of the curved layer sieve was 30 mm and the vertical spacing H was 45-65 mm. Taking the vertical spacing H of the curved layer sieve, the curvature U of the curved mesh hole, and the spacing S of the curved mesh hole as the experimental factors, considering the screening efficiency α and the impurity content β of the jujube as the response values, the three-factor three-level quadratic regression orthogonal experiment was designed, establishing the regression mathematical model of each factor and response value, and the multiple target optimization algorithm of Design-expert software was used to optimize various factors. The results showed that the influence factors on the screening efficiency were in the descending order as: the arc screen spacing, the vertical spacing of the curved layer screen, and the curved screen hole curvature; The significant factors affecting the impurity content of jujube were in the descending order as: the arc screen spacing, the curved screen hole curvature, and the vertical spacing of the curved layer screen. The experimental results were verified by the optimized combination of parameters: when the vertical spacing H of the curved layer screen was 65 mm, the curved screen hole curvature U was 110°, and the arc screen spacing S was 23 mm, the average screening efficiency α in the test was 91.09%. The relative error between the experimental verification value and the theoretical optimization value was 1.36%, which was less than 5%. The impurity content of jujube β in the test was 1.02%. The relative error between the experimental verification value and the theoretical optimization value was 2.00%, which was also less than 5%. The test results can provide a reference for the research and optimization of the subsequent air-suction-type jujube harvester cleaning device.