The all-round penetration of artificial intelligence technology has brought about a drastic change in the educational landscape, and the teaching system of colleges and universities relies on artificial intelligence technology to expand its own boundaries, leading to interdisciplinary knowledge fusion between dual colleges and universities. With the support of AI technology, a teaching system design idea of interdisciplinary knowledge integration is proposed, and a teaching innovation system of interdisciplinary knowledge integration between dual colleges and universities is established. Taking the learners’ interdisciplinary knowledge point response situation as an entry point, input modeling is carried out for the learners’ interdisciplinary knowledge points, forgetting coefficient, etc., and the dual colleges’ interdisciplinary knowledge tracking SA-BiGRU model is established by combining BiGRU and the attention mechanism, and simulation verification is carried out to verify its effectiveness. Taking a vocational college in province G as an example, a dual college interdisciplinary teaching comparison experiment was designed in combination with the teaching innovation system, so as to verify the effectiveness of the interdisciplinary knowledge integration teaching innovation system. The results show that the AUC and ACC of the SA-BiGRU model can reach up to 0.837 and 0.841 respectively in interdisciplinary knowledge tracking, and the learners’ interdisciplinary knowledge reserve and ideological literacy level have been improved by 1.36 and 1.82 points respectively compared with that before the experiment. Relying on artificial intelligence technology can promote interdisciplinary knowledge integration, provide a new research direction for the development of interdisciplinary intelligence in BiGR, and lay the foundation for the cultivation of highly skilled and qualified applied talents.

Smart campus relies on IoT technology to realize teaching management, location monitoring, business processing and other teaching and management activities, this paper draws on the characteristics of the development of smart campus, and builds a decision support system for educational management of smart campus by applying the conditions of IoT technology. The IoT multi-sensor is used to collect educational management data, and the Grobes criterion is applied to exclude the data with too large an error, and the consistency test is performed on the collected data. The least squares method and variance calculation are combined to process the multi-sensor data to optimize the data fusion accuracy. Comparison tests were conducted to analyze the fusion accuracy and variance of the observed data under different methods. Distribute questionnaires online and offline to analyze the feasibility of the construction of IoT in smart campus. Collate the ratings of teachers and students on the educational management decision support system of the smart campus, in which the ratings of teachers and students on the educational management decision part of the school are concentrated in the range of 0.7 to 0.8, and the overall rating of the educational management decision support system of the smart campus is 86.453 points.

Energy, as one of the larger contributing industries to greenhouse gas emissions, has an urgent task to reduce emissions, and standardizing the carbon footprint and trading mechanism of the energy market is an important concern for the development of the current energy industry. Under the guidance of the principle of green, low-carbon and sustainable development of the energy market, this paper first uses heterogeneous blockchain and federated reinforcement learning to design a decentralized energy trading mechanism model. It is found that the model fails to realize the intelligent detection and control of carbon footprint, in this regard, on the original model, the carbon footprint origin algorithm is introduced. Combining the above models and algorithms, the current interactive energy market is explored and analyzed. Consumer user 5 has the largest net benefit, with a specific value of 15.05 million yuan, and comprehensive energy supplier 3 has the largest net benefit, with a value of 37,467,000 yuan, indicating that this paper’s model implements the principle of green, low carbon and sustainable development of energy while meeting the energy needs of consumers and suppliers, maximizing the interests of each other in the process of energy trading, which proves that this paper’s research has excellent practical application value.

OMO teaching mode based on artificial intelligence big model is one of the important future research directions and application landing forms in the future education field. The learning path recommendation algorithm based on big language model is constructed by integrating Transformer architecture, neural network architecture and self-attention mechanism. Combining it with the course knowledge graph, it links the learners with the knowledge system and visualizes the results of the intelligently planned learning path. The study shows that compared with several other algorithms, the personalized learning path recommendation algorithm based on AI big model has better convergence speed and stability. The optimal solution for learning path planning is found after only about 90 iterations. Taking “Chemical Process and Control Simulation” as the target course, the method in this paper gives the learning path and course. Through the questionnaire survey, the mean value of the four dimensions of pre-class pre-study, classroom exploration, post-class enhancement, and learning satisfaction is more than 3 points, which indicates that the OMO model and the teaching model of the artificial intelligence big model have a better experience.

Accurate distribution system topology is of great significance for distribution network planning operation and analysis. This project constructs a distribution system network model, applies graph convolutional network and graph attention network in graph neural network, and designs the topology identification method of distribution system. On this basis, a reconfiguration model of the distribution system is given, and the network structure after topology identification is used for trend calculation, and the model reconfiguration is realized by using the extensive learning quantum evolutionary algorithm. Through experimental analysis of several test systems, it is found that the topology identification F1 values of this paper’s method are all above 0.9, which are 5.64% to 29.64% higher than other methods, confirming the good accuracy and robustness of the GNN topology identification model. In addition, the CLQIEA method can give the correct distribution system reconfiguration optimization scheme, which reduces the network loss to a larger extent and improves most of the node voltage values, and the network loss decreases by 31.91% and 56.11%, and the voltage values are improved by an average of 1.95% and 1.23% in the two test systems, which makes the power supply of the distribution system of a higher quality, and the operation of the power supply system is more economical, which is important for the distribution automation and the power supply department’s optimal scheduling is of great significance.

On the basis of ensuring the balance between supply and demand of the power grid, fully realizing the automatic control of the air conditioning system can make the energy consumption of the air conditioning operation reduce significantly, thus realizing the purpose of energy saving. This paper combines a variety of technologies to establish an intelligent air conditioning measurement and control system, realizes terminal communication through the CoAP protocol, and designs the corresponding system hardware as well as the real-time data acquisition method for air conditioning equipment. Based on the PID principle, the temperature and humidity control strategy of air conditioning equipment based on expert PID is proposed. In order to better ensure the energy-saving control efficiency of air-conditioning equipment, this paper fully considers human thermal comfort and the interaction between supply and demand of the power grid, establishes a comprehensive optimization control model with the objectives of user power consumption and human comfort, and passes through the PSO algorithm in order to obtain the optimal control results. Simulation found that when the initial temperature is lower than the set value, the expert PID control strategy will adaptively realize the air conditioning temperature and humidity adaptive regulation to ensure that the indoor temperature is within a reasonable range. The total power consumption of the grid is reduced by 90.18kW compared with that before optimization, and the maximum value of human comfort evaluation is improved by 11.39%. Relying on the intelligent air conditioning control system, the adaptive control of temperature and humidity can be effectively realized and the indoor air quality can be better ensured, and a reliable control strategy can also be provided to ensure the balance between supply and demand of the power grid.

This paper follows the active reactive power cooperative control strategy of station voltage autonomy, combines the operation scenarios of the autonomous control strategy within the group, and establishes the reactive power optimization objective function of the low-voltage distribution network to improve the voltage quality and reduce the active loss, which takes into account the installation location of reactive power compensation device, and the constraints include the system power balance constraints and voltage quality constraints. In order to solve the reactive power optimization model of low-voltage distribution network containing distributed photovoltaic, the uniformity of the population distribution of the MPA algorithm is initialized using Bernoulli mapping, the inertia weight function and elite strategy of nonlinear attenuation are introduced to enhance the optimization capability of the MPA algorithm in the iterative process, and the eddy-current and fish aggregation effects are applied to widen the scope of optimization search. The network loss and voltage amplitude of the proposed strategy are analyzed to compare the changes of node voltage, voltage offset, objective function value and branch circuit active loss before and after the voltage autonomous reactive power control of low voltage stations. After adopting the optimization strategy of voltage autonomous reactive power control for LV stations, the branch circuit active loss of LV distribution network decreases with the increase of the proportion of distributed PV, and the branch circuit active loss of LV distribution network can be reduced by up to 60%.

Bitumen is a high-quality raw material for the preparation of carbon materials due to its high carbon and low ash characteristics, and its use in the preparation of supercapacitor electrode materials plays a significant role in the enhancement of the economic benefits of the entire coal chemical process. In this paper, the raw materials and experimental equipment required for this study were selected to prepare porous carbon samples under the guidance of the raw material pretreatment process. After completing the preparation of porous carbon samples, the finite element analysis software ANSYS was used to investigate the effect of bitumen pretreatment on the structure and electrochemical properties of porous carbon. With the rising air oxidation time, the peak ratio of porous carbon showed a trend of decreasing and then increasing, with specific values of 2.627, 1.958, 2.083, and 2.486, which was the same trend as that of the XRD test results, suggesting that the asphalt pretreatment has a moderating effect on the structure of porous carbon. The study in this paper further recognizes the effect of asphalt pretreatment on the structure and electrochemical properties of porous carbon, which provides a reference for research and development and innovation in materials chemistry.

Asphalt mixture is a multiphase composite material composed of aggregates, asphalt, fillers and other materials of different properties, in which the coarse aggregate forms the main bearing structure, and the fine aggregate fills the voids formed by the coarse aggregate to improve the structural stability. In this paper, computerized tomography is used to obtain the preliminary tomographic images of asphalt mixture specimens, and the image is effectively segmented through the grayscale thresholding method, and the scanning results are refined. Using voxel-based three-dimensional reconstruction method, the three-dimensional finite element model of asphalt mixture is reconstructed, and the corresponding fine structural characterization index is proposed to prepare asphalt mixture specimens and study the fine structural characteristics of asphalt mixture. The distribution characteristics of the contact connectivity tree of the asphalt mixture are analyzed, with 61.54% of the primary and middle order trees in gradation 1, 92.31% in gradation 2, 83.33% in gradation 3 and 58.82% in gradation 4. It shows that the higher the percentage of second-order connectivity tree, the worse the skeleton contact connectivity, which is not conducive to the improvement of asphalt mixture shear strength. For the four different gradation specimen slice images, the generated areas of each order tree were statistically analyzed. Most of the primary order tree areas were distributed between 100 mm²-300 mm², the intermediate order tree areas were basically distributed between 200 mm²-400 mm², and the high order trees were distributed between 400 mm²-500 mm². The area distribution of high-order tree of grade 4 is more uniform and concentrated, which has better load transfer chain and rutting resistance.

Traditional digital signatures are often publicly verifiable, and in certain applications with privacy preservation requirements, the signer does not want the sensitive information it signed to be redelivered by a dishonest verifier. Aiming at the problem that traditional chameleon signatures (CS) cannot resist quantum computer attacks, this paper proposes a lattice-based authentication CS scheme. Based on the analysis of the lattice difficulty problem and the security vulnerability of the CS scheme, it is pointed out that it does not satisfy the third-party unforgeability and the signer rejectability, and a new lattice-based identity CS scheme is established, which is verified under the stochastic predicate machine model, and the storage and transmission efficiency of the scheme is analyzed. The results show that the newly designed identity-based CS scheme on the lattice can effectively resist quantum computer attacks, can sign messages of arbitrary length, and possesses more lightweight storage and transmission efficiency. The optimized chameleon signature scheme has better security and also provides a new solution for digital signatures to resist quantum computer attacks.