2329 results about "Thermal load" patented technology

The invention relates to the technical field of air conditioner chilled water control, in particular to an air conditioner chilled water control method and system based on deep learning, and the method comprises the following steps: collecting states of an air conditioner water chilling unit, including water pump frequency and valve opening feedback, and pipe network water supply temperature, return water temperature, flow and differential pressure operation readings; according to the method, the state parameters of the water chilling unit are dynamically collected, the system operation state feature set is constructed, real-time fusion and standardization processing of multi-source heterogeneous data are achieved, the problem of time sequence dislocation caused by sensor sampling frequency differences is solved, the heat load change key input quantity is recognized based on the feature set, and the system operation state feature set is established. And the performance attenuation trend of the water pump is accurately pre-judged in combination with prediction calculation, and extra energy consumption caused by lagging adjustment is reduced. A layered optimization framework with total energy consumption minimization as a target is introduced, water supply temperature, pressure difference setting and unit operation combination are decoupled into independent optimization sub-problems, and invalid work of a water pump is reduced on the premise that the tail end heat requirement is met.

The invention relates to the technical field of new energy automobile thermal management, in particular to a direct cooling and heating management system and method in an automobile power battery. The method comprises the following steps: acquiring vehicle real-time operation condition data and battery pack state monitoring data; working condition mode recognition processing is conducted according to the vehicle real-time operation working condition data, and vehicle working condition mode feature data are generated; performing thermal load demand analysis on the battery pack state monitoring data based on the vehicle working condition mode characteristic data to obtain dynamic thermal load demand data of the battery pack; and according to the dynamic thermal load demand data of the battery pack, refrigerant demand quantity calculation and analysis are carried out, the refrigerant supply capacity of the current direct cooling system is evaluated, and refrigerant supply and demand matching feature data are obtained. The specific requirements of three heat sources of the battery, the motor and the cockpit for the refrigerant flow are quantified, and a refrigerant distribution strategy is formed according to the proportional relation, so that the safety of the battery is improved, and the driving comfort and the working stability of the electric driving system are also guaranteed.

The invention relates to the technical field of data processing, and provides a multi-heat-source networking heat supply optimization operation method and system.The method comprises the steps that environmental parameters, heat source data, market dynamic information, user behavior characteristics and a pipe network topological graph are collected by deploying IoT equipment; acquiring a thermal load time sequence predicted value in a future preset time period; the heat source data and the pipe network topological graph are processed, and a pipe network operation state matrix is obtained; performing feature dimension alignment processing on the pipe network operation state matrix to obtain a pipe network spatial topology feature mapping value; performing weighted fusion on the thermal load time sequence prediction value and the pipe network spatial topological feature mapping value to obtain a final thermal load prediction value; and optimal operation of heat supply is realized according to the final heat load predicted value. According to the method, a real-time response mechanism for environmental parameters, market dynamics and user behavior characteristics can be realized, collaborative optimization of multiple heat sources can be realized, the heat source collaborative efficiency is improved, and energy waste and operation cost are reduced.

The invention discloses a server mainboard regional distributed liquid cooling heat exchange adjusting method, which comprises the following steps of: acquiring a temperature parameter set and a power consumption parameter set of each monitoring region in real time, and generating a thermal load parameter feature vector; identifying a high heat load core area set according to the heat load parameter feature vector; generating a liquid cooling branch flow distribution instruction set based on the position distribution of the high heat load core area set; executing the liquid cooling branch flow distribution instruction set, and obtaining an adjusted temperature feedback parameter set; according to the deviation degree of the temperature feedback parameter set and the target temperature interval, dynamic feedback adjustment is carried out by applying the heat conduction compensation coefficient and the fluid viscosity-temperature compensation coefficient, and an updated liquid cooling branch flow distribution instruction set is generated. The method has the following advantages and effects that by sensing the thermal load space distribution characteristics of all areas of the mainboard in real time, cooling flow distribution is dynamically adapted, real-time compensation of the fluid viscosity-temperature effect is integrated, local hot spots are eliminated, and the heat dissipation effect is improved.

The invention relates to the technical field of energy storage management, in particular to a high-energy-density liquid cooling energy storage system based on thermal management optimization, which comprises a thermal response calculation module, a thermal risk area identification module, a cooling resource allocation module, a thermal decoupling state judgment module and a charging and discharging power limiting module. According to the method, the inlet temperature, the outlet temperature and the cooling liquid flow speed of the high-energy-density energy storage equipment are obtained, the unit thermal load conversion rate is calculated, the unit thermal response deviation degree is determined, the thermal risk area higher than the standard limit is clearly recognized in the energy storage equipment, the corresponding liquid cooling channel is accurately selected, and the cooling liquid pulse flow frequency is optimized; the pertinence and timeliness of the cooling liquid in actual use are effectively improved, the local overheating hidden danger is avoided, the lag response is marked in time by monitoring the cooling liquid pressure difference and the temperature rise change in real time, the decoupling state between the cooling liquid and the thermal load is judged, the charge and discharge power dynamic reduction measure is implemented, and the trend of abnormal and continuous accumulation of the local thermal load is restrained.

The invention provides a lithium battery equalization thermal management method. Real-time temperature data is obtained by constructing a thermal distribution monitoring network, the temperature difference between a center and an edge area is analyzed, a thermal load distribution coefficient is calculated, and a dynamic heat dissipation intensity adjustment model is established; driving the multi-channel cooling system to operate according to the heat dissipation demand priority, and adjusting the flow distribution proportion of a cooling medium; a dynamic nonlinear feedback correction mechanism is adopted, secondary adjustment is carried out for uneven temperature distribution, and an optimal heat dissipation parameter combination is determined in combination with historical data. Uniformity control over temperature distribution of the battery module is achieved, the problem of heat accumulation in a center area is effectively solved, the heat dissipation efficiency under the rapid charging working condition is improved, and the safety performance and the service life of the battery module are guaranteed.

The invention relates to the technical field of heat load prediction, and discloses a heat supply system load prediction method and system, and the method comprises the steps: collecting multi-source sensing data in real time, and collecting outdoor meteorological parameters and building structure information; based on building distribution, a pipe network structure and user load characteristics of a heat supply area, a multi-stage heat supply load prediction model is constructed. And constructing a thermal topological graph model of the heat supply area based on the graph neural network. And periodically collecting parameters of the building-level edge prediction model, the heat exchange station-level aggregation prediction model and the thermal topological graph model, performing global aggregation optimization, and updating and optimizing each edge node model. And obtaining an edge prediction result according to the optimized model, and jointly controlling the heat source output power, the main pump rotating speed and the area valve opening according to the edge prediction result and the heat source level scheduling prediction model. According to the method, the depiction capability of the system on the dynamic load change and the space heat conduction path is improved, and the generalization capability of model updating and the real-time responsiveness of edge deployment are ensured.

The invention discloses a dynamic intelligent control method and system for improving the efficiency of a rectifying tower, particularly relates to the technical field of chemical process control, and is used for solving the technical defect that an operation variable is mismatched with a physical state due to the fact that an existing distributed control system cannot recognize a hidden degradation state of equipment. The method comprises the following steps: acquiring temperature gradient distribution of each tower plate of a rectifying tower, thermal load of a reboiler and tower top condensation load parameters in real time, calculating a mass transfer efficiency offset by combining the temperature gradient distribution to generate a scaling trend index, and synchronously calculating a local entropy yield based on the thermal load and the condensation load to generate a thermodynamic irreversibility index. When the double indexes exceed a preset threshold value, it is judged that a recessive degradation state is entered, then a backflow ratio correction coefficient is reversely derived through a dynamic correlation model, and the correction coefficient is input into a distributed control system to dynamically adjust backflow ratio operation parameters; the product purity is maintained, the tower plate scaling process is obviously delayed, and long-term efficient operation of the rectifying tower is guaranteed.

The invention provides a heat supply load prediction and scheduling method based on energy storage peak regulation, and the method comprises the steps: obtaining multi-modal data of a heat supply system, carrying out the preprocessing of the multi-modal data, and constructing a space-time joint feature matrix based on the preprocessed multi-modal data; inputting the spatio-temporal joint feature matrix into a multi-modal depth load prediction model for heat supply load prediction to obtain a heat supply load prediction result; the multi-modal deep load prediction model is obtained by training a deep learning prediction model fused with physical constraints through system historical data; based on the heat supply load prediction result, a distributed energy storage scheduling strategy is generated in combination with a multi-agent reinforcement learning algorithm based on an MADDPG framework, and scheduling operation of the heat supply system is carried out according to the distributed energy storage scheduling strategy; and the energy utilization efficiency and the power grid stability are improved.

The invention discloses a dynamic flow control method for a two-phase cold plate liquid cooling system based on multi-modal sensing, and relates to the technical field of equipment cooling. Comprising the following steps: S1, collecting liquid cooling monitoring data in real time, and performing data preprocessing; s2, judging the state risk of the cold plate, carrying out signal cross validation, and taking an abnormal regulation and control measure; s3, cooling liquid flow regulation and control are carried out, and the matching degree of flow regulation and control and chip thermal load is evaluated, so that flow regulation and control correction is carried out; and S4, constructing a big data modeling and simulation feedback platform, evaluating a flow regulation and control self-healing effect, optimizing each parameter and strategy, and carrying out self-learning evolution. The problems that an existing two-phase cold plate liquid cooling system generally only depends on a single temperature signal, lacks a multi-source redundancy check mechanism, has the problems of response lag, weak local reflection capacity, high risk during failure and the like, consequently, the cooling capacity distribution and adjustment precision is insufficient, and the actual requirement of a high-heat-density data center for heat dissipation is difficult to meet are solved.

The invention discloses a heat supply system multi-working-condition scheduling control method based on a large model and multiple agents. The method comprises the steps that a heat supply system digital twinborn model is established; the method comprises the following steps: setting a scheduling control center management agent, predicting a thermal load demand by adopting a large language model and combining a thermal load prediction model, dividing a system into a plurality of operation conditions, and setting a plurality of condition sub-agents corresponding to the operation conditions; the dispatching control center management agent judges whether the working condition sub-agents under the corresponding operation working conditions are triggered to start working or not, and meanwhile heat load demand values, predicted through a large language model, of all time periods in the future and the heat production amount of the new energy heat supply unit are transmitted to the corresponding working condition sub-agents; and the working condition sub-agent adopts a large language model to establish a system optimization scheduling control knowledge graph based on the large language model, obtains a scheduling control strategy of each device on the source network load side of the heat supply system, and feeds back the scheduling control strategy to the digital twinborn model for guiding the actual operation management of the heat supply system.

The invention provides a distributed intelligent cooperative energy-saving control method and device for an industrial air conditioner, electronic equipment and a computer readable storage medium, and is applied to the field of data processing application. The method comprises the following steps: acquiring industrial air conditioner operation related data including environment parameters and equipment state data; an intelligent cooperative control mechanism is constructed based on multi-device cooperation and hierarchical adjustment requirements, and the intelligent cooperative control mechanism comprises a multi-device linkage strategy for dynamically distributing refrigeration resources according to regional cooling and heating loads and a hierarchical adjustment algorithm of a chilled water system and a cooling system, and a control framework for achieving global optimization is formed; processing the environment parameters and the equipment state data to generate a dynamic control strategy; generating target energy-saving control information based on the data analysis result and the dynamic control strategy; and all operation data and control effects generated based on the target energy-saving control information are integrated, a high-energy-consumption link optimization scheme is generated, energy consumption data credible tracing is achieved, and the distributed air conditioning system is aggregated to participate in power grid frequency modulation.

The invention provides a cooling structure of a motor stator, an oil-cooled motor and a vehicle, and belongs to the technical field of automobiles. A guide oil duct and a stepped oil injection duct are arranged on a stator core; the middle of the stator iron core is provided with an oil inlet groove surrounding the stator iron core in the circumferential direction, and a cooling medium enters the flow guide oil channel through the oil inlet groove in the middle of the stator iron core and obliquely injects oil to the stator windings at the two ends of the stator iron core through the stepped oil injection channel. According to the invention, the oil path is directly arranged on the stator core and the stepped oil injection channels are symmetrically arranged, and the cooling medium can be intensively and obliquely sprayed to the surface of the stator winding through the stepped oil injection channels, so that the heat dissipation effect and the heat dissipation efficiency are improved, and the thermal load capacity of the motor and the working efficiency of the motor are further improved; and faults of the motor caused by non-uniform cooling, overhigh local temperature rise and temperature gradient are reduced. The structure is simple, and the overall manufacturing and maintenance cost is reduced; meanwhile, the overall size of the motor is reduced, and overall light weight is facilitated.

The invention discloses a low-carbon flexible coal-fired unit power control system and method, and relates to the technical field of power systems, and the system comprises a cascade waste heat recovery module, a boiler deep regulation and control module, a thermal coordination module, an environmental protection and emission reduction module, an intelligent operation scheduling module and an energy efficiency monitoring module. The gradient waste heat recovery module carries out gradient recovery on flue gas heat energy according to temperature zone grades; the boiler depth regulation and control module is used for regulating combustion air supply and heat absorption paths to realize low-load stable combustion; the thermal coordination module dynamically distributes thermal loads between the multiple heat sources and the thermal units; the environmental protection and emission reduction module jointly controls desulfurization, denitration and wastewater resourceful treatment; the intelligent operation scheduling module generates a load regulation and control instruction and coordinates multi-module response; the energy efficiency monitoring module collects and analyzes energy consumption and emission indexes and assists strategy optimization. The energy efficiency utilization and emission control capability of the unit under the deep peak regulation condition is improved, and flexible, efficient and low-carbon operation is achieved.

The invention relates to the technical field of intelligent regulation and control of a heat supply system, in particular to a heat supply system hydraulic unbalance real-time correction method and system based on federated learning, and the method comprises the steps: constructing a temperature prediction model based on an LSTM neural network, deploying federated nodes at each user side, collecting multi-dimensional heat supply data in real time, and carrying out the preprocessing; local model parameters are encrypted and uploaded to a central server through a federated learning framework, global model parameters are generated based on verification set error dynamic weighted aggregation, and nodes are reversely updated; the updated model is used for predicting the heat load in the next one hour, the valve opening degree is dynamically adjusted in combination with a hydraulic equilibrium algorithm, and whole-network flow and heat demand matching is achieved. According to the method, data privacy is guaranteed through federated learning and a block chain technology, edge calculation and LSTM time sequence prediction are combined, the problems that a traditional method is high in data transmission delay, high in privacy risk and poor in model generalization are solved, and the real-time response capability and the energy utilization efficiency of a heat supply system are remarkably improved.

The invention discloses an intelligent control system and method for a multi-unit parallel water-cooling refrigerator, and belongs to the technical field of refrigeration equipment. The control system comprises a data acquisition module, a load prediction module, an energy efficiency optimization module and a cooperative control module. The data acquisition module is used for acquiring the running state and environmental parameters of the refrigerator in real time; the load prediction module is used for predicting the refrigerator thermal load based on the operation state and the environmental parameters; the energy efficiency optimization module is used for optimizing operation parameters of each unit according to the predicted thermal load of the refrigerator; and the cooperative control module is used for cooperatively controlling the compressor frequency and the cooling water flow of each unit according to the optimized operation parameters. According to the intelligent control system and method for the multi-unit parallel water-cooling refrigerator, precise temperature control and energy efficiency optimization of the multi-unit parallel water-cooling refrigerator can be achieved, load and water flow distribution is uniform, temperature fluctuation is small, system energy consumption is low, and the temperature control and energy saving requirements of a high-quality cold chain can be met.

The invention relates to the technical field of industrial control, and discloses a dry-wet combined cooling tower operation state prediction and diagnosis system comprising a load prediction module used for obtaining production plan data and environment information, constructing a basic heat load prediction model, and outputting a total prediction heat load; the thermal modeling module is used for establishing a heat transfer model and an energy consumption model, the heat transfer model outputs cooling amounts in different operation modes, and the energy consumption model outputs total predicted power; the dry-wet decision module is used for constructing a multi-objective optimization function and solving the multi-objective optimization function to obtain a dry-wet switching strategy; and the control execution module is used for executing the dry-wet switching strategy. According to the method, the basic thermal load prediction model is established, so that the prediction precision of the thermal load is improved, and differentiated cooling strategies are provided for different production stages; on the basis of real-time load requirements and environmental conditions, a dry mode or a wet mode is intelligently selected for operation, and a multi-objective optimization function is constructed, so that the balance between cooling requirement meeting and system energy consumption minimization is realized.

The invention relates to an intelligent energy-saving method for a large building refrigerating system based on a large language model, and belongs to the field of intelligence of large building refrigerating systems. A reinforcement learning framework is constructed, a multi-dimensional state space formed by building thermal loads, equipment operation states and thermal environment parameters is defined, and a dynamic reward mechanism is designed by taking improvement of energy efficiency, guarantee of thermal safety constraints and maintenance of thermal comfort as optimization objectives; developing a word embedding model special for the refrigeration field and a cross-modal decision conversion model, and realizing bidirectional analysis of a natural language instruction and a physical control parameter through feature coding and embedding mapping; and performing low-rank adaptive fine tuning on the pre-trained large language model based on the reinforcement learning experience set, and constructing a closed-loop verification system. Generalized migration and multi-target collaborative decision-making of equipment control strategies are achieved, the self-adaptive regulation and control capacity of a refrigeration system under dynamic loads is improved, and a universal intelligent solution for energy efficiency optimization, thermal safety and comfort is provided for a large building.

The invention relates to the technical field of turret heat management, in particular to a power turret heat management optimization method and system based on intelligent cooling, and the method comprises the steps: obtaining the temperature distribution data and related working condition parameters of a power turret in real time, and building a heat state feature vector representing the dynamic relation between the heat generation and heat dissipation capability of the turret; constructing a cooling decision model, inputting the state vector into the cooling decision model, and generating an initial control strategy; the initial control strategy is simulated and executed in the digital twin environment, and a strategy reconstruction mechanism is triggered when the predicted temperature suppression rate is lower than a set threshold value; and performing real-time dynamic optimization on the verified initial control strategy according to the processing quality constraint and the equipment safety threshold, and superposing the thermal inertia delay compensation amount to generate a final control strategy. According to the method and the device, the problem of temperature control failure caused by thermal inertia time lag is effectively solved, accurate space-time matching of the cooling instruction and the thermal load peak value is realized, and thermally induced deformation is remarkably inhibited.

The invention discloses a water-cooling energy consumption adaptive regulation and control method suitable for a data center, and the method comprises the following steps: obtaining a multi-dimensional operation parameter set of the data center in real time, and generating a real-time thermal load density distribution diagram reflecting the heat distribution condition in a machine room; calculating the overall thermal deviation degree and the local hot spot intensity, and solving through a dynamic energy efficiency optimization function to obtain a target system supply and return water temperature difference and a target cooling liquid flow; inputting into a hydraulic and thermodynamic simulation model, and generating an optimal multi-device coordinated regulation instruction set; and executing the multi-device coordinated regulation instruction set, and then performing parameter calibration on the hydraulic and thermodynamic simulation model. The method has the following advantages and effects that the thermal environment of the machine room can be sensed in real time, the energy consumption and heat dissipation requirements can be intelligently balanced, and multiple devices in the cooling system can be cooperatively regulated and controlled, so that the overall energy consumption of the cooling system is optimized while the local overheating risk of the machine room is thoroughly eliminated.

The invention discloses a ship fuel cell cooling system energy efficiency management method based on deep reinforcement learning, and relates to the technical field of ship energy management, and the method comprises the steps: constructing a digital simulation model of a ship fuel cell cooling system, which is used for representing the dynamic characteristics of the cooling system under different working conditions; constructing a multi-time scale prediction and thermal load prediction model, and respectively outputting cooling system state and working condition prediction parameters and thermal load prediction parameters under different time scales; a reinforcement learning framework based on the dual deep Q network is built, a state space, an action space and a reward function are defined, and the state space comprises current state parameters of the cooling system and output parameters of all prediction models; the action space comprises seawater pump rotating speed, fresh water pump rotating speed and regulating valve opening; and an optimal control strategy is generated based on a training result of deep reinforcement learning, and global collaborative optimization operation of execution equipment of the cooling system is realized, so that the system energy efficiency and environmental adaptability are improved.

The invention relates to the technical field of temperature control of high-precision industrial heating equipment, in particular to an anti-interference precise temperature control method and system for heating an upper die, and the method comprises the steps: starting a multi-region heating array, heating the upper die to a target temperature according to a preset temperature rise curve, and building a uniform thermal field; before the high-pressure medium is introduced, heat load change caused by the high-pressure medium is predicted based on medium process parameters; in the medium introduction process, dynamic anti-interference compensation control is executed, a feedforward power compensation instruction based on a thermal load and a feedback power fine tuning instruction based on temperature deviation are generated respectively, and the feedforward power compensation instruction and the feedback power fine tuning instruction are weighted and fused into a composite power driving signal for adjusting a heating array; when the temperature fluctuation converges to a stable threshold value, the feedforward compensation weight is gradually reduced, smooth switching to steady-state control is achieved, transient thermal shock caused by a high-pressure medium is effectively restrained through feedforward and feedback cooperative compensation and dynamic weight adjustment, the temperature fluctuation is reduced, and the temperature control precision and stability are improved.

An automatic control system of an air source heat pump analyzes collected multi-dimensional operation parameters in real time based on a machine learning algorithm, constructs a high-precision thermal load prediction model, predicts thermal load requirements in the future 1-24 hours, controls prediction errors within 5%, and achieves minimization of energy consumption and maximization of heat storage efficiency on the premise of meeting operation constraints. The overall energy consumption is reduced by 15%-25% compared with that of a traditional system, the heat loss is reduced by dynamically adjusting the flow of a heat storage medium and optimizing the thermodynamic process of heat storage and heat release, and the heat storage efficiency is improved by 10%-15%. According to the invention, the advanced machine learning algorithm is adopted through the big data analysis module, the multi-dimensional operation parameters are analyzed in real time, a high-precision thermal load prediction model is constructed, the thermal load demand in the future 1-24 hours is predicted, and the prediction error is controlled within 5%.

The invention relates to the technical field of intelligent buildings and energy management, and particularly discloses an intelligent building heating intelligent optimization operation method and system based on deep learning, and the method comprises the steps: collecting building environment parameters and equipment operation data in real time through a distributed optical fiber sensing network and an infrared thermal imaging system; extracting minute-level fluid transmission and distribution parameters and hour-level building thermal inertia characteristics by adopting wavelet packet transformation and a graph neural network; then, constructing a neural differential equation prediction model fused with physical constraints, and outputting high-precision thermal load demand prediction through a differentiable heat conduction operator coupling multi-time scale feature; then, a mixed integer optimization model considering equipment life loss is established, and boiler start-stop combination and pipe network flow distribution are synchronously optimized by adopting a hierarchical decision-making mechanism; and finally, closed-loop control is realized through a multi-mode actuator network, and model parameters are dynamically adjusted in combination with an online learning mechanism.

The multi-energy complementary heat supply system comprises an external basic heat source, a middle-grade synergistic heat source, a high-grade energy storage heat source, an intelligent heating power mixing center and a central controller, and the intelligent heating power mixing center is used for heating heat source equipment of all levels and operation instructions of associated assemblies according to the operation instructions of the heat source equipment of all the levels and the operation instructions of the associated assemblies. Heat energy of different grades is mixed and allocated, and heat loads meeting the grade requirements of heat consumers are output to the heat consumers; the central controller is used for establishing a multi-target optimization model taking the minimum total operation cost of the system as a core target based on the electricity price prediction data and the different-grade thermal load prediction data, solving the multi-target optimization model and generating a system operation strategy under the condition that preset basic guarantee logic, economic operation logic and peak response and power grid interaction logic are met; and the generated system operation strategy is converted into an operation instruction for the heat source equipment of each level and the associated assembly, so that the reliability and the adaptability of operation control of the heat supply system are effectively improved.

The invention discloses a land energy storage container self-adaptive liquid cooling heat dissipation device and method, the device comprises a liquid cooling unit, a self-adaptive circulation pipeline, a variable flow pump valve group, a distributed temperature sensing module and a BMS main control module, through data monitoring, model establishment, thermal load prediction, selection of a proper cooling mode, and introduction of reasonable compensation, the self-adaptive liquid cooling heat dissipation of the land energy storage container is realized. And the variable-frequency circulating pump and the valve body are adjusted and combined for execution. Through multi-parameter fusion control, dynamic impedance matching and intelligent algorithm optimization, a cooperative control mode of a variable orifice regulating valve and a variable frequency circulating pump is innovatively adopted, and dynamic matching of cooling loop impedance is achieved; through temperature field modeling, heat dissipation demand grading prediction, a cooling parameter self-optimization algorithm and fault self-diagnosis, the balance degree of the temperature field is effectively improved, heat dissipation energy consumption is reduced, environmental adaptability is enhanced, and meanwhile the method has the advantages of being high in reliability, wide in environmental adaptability and low in operation and maintenance cost.

The invention relates to the technical field of electric workover rig thermal management, and discloses a workover pump truck electric drive thermal management method and system, and the system comprises a multi-source temperature collection module, an operation state monitoring module, a thermal management analysis module, a strategy matching engine module, a dynamic execution control module, a feedback optimization module, and a prediction decision module. The method comprises the following steps: acquiring environment temperature, motor temperature, battery temperature and cooling liquid temperature data; obtaining motor power, battery current and a vehicle operation mode; generating a thermal management demand level based on the temperature and the operating parameters; matching natural cooling, air cooling or liquid cooling strategies according to grades; cooling operation is executed, the temperature change rate is calculated in real time, and the cooling intensity is dynamically adjusted; when the threshold value is exceeded, liquid cooling cooperative control is started; predicting a thermal load trend through an LSTM model, generating a dynamic cooling plan, and optimizing an execution priority; and a thermal management efficiency evaluation report is output, so that the operation reliability and energy efficiency of the electrically-driven workover pump truck are improved.

The invention relates to the technical field of electric welding machines, in particular to a dynamic heat dissipation control method and system for an intelligent electric welding machine. A heat load real-time calculation and heat accumulation trend prediction step; a dynamic collaborative heat dissipation strategy generation and execution step: dynamically generating and executing an air cooling heat dissipation strategy, an air cooling and liquid cooling collaborative heat dissipation strategy or a protective heat dissipation strategy according to a comparison result; wherein the control parameters of the air cooling heat dissipation strategy are determined according to the difference value between the predicted temperature and the corresponding threshold value and the environment temperature; the control parameters of the air cooling and liquid cooling collaborative heat dissipation strategy are determined according to the difference value between the predicted temperature and the corresponding threshold value and the environment humidity; and a heat dissipation effect feedback and self-adaptive calibration step. Real-time sensing, thermal load prediction, a dynamic heat dissipation strategy and feedback calibration are combined, the heat dissipation strategy can be dynamically adjusted according to the working environment and the operation state of the electric welding machine, and the stability and reliability of equipment are improved.

The invention discloses a liquid cooling heat dissipation control method and device for a high-power charging pile, and the method comprises the steps: obtaining the temperature data of a heating element in the charging pile and external environment parameters, building a dynamic heat load distribution model through a pre-built heat conduction algorithm according to the incidence relation between the temperature data and the charging power, and achieving the heat dissipation of the charging pile. Obtaining heat distribution characteristics; according to the heat distribution characteristics, in combination with a preset heat dissipation efficiency threshold value and a power density requirement in the liquid cooling heat dissipation control system, the cooling liquid flow and the cooling liquid circulation rate under the current working condition are calculated, and a cooling liquid distribution scheme containing a flow distribution proportion and a circulation path is determined; and if it is detected that the external environment temperature in the external environment parameters exceeds a preset threshold range, corresponding environment challenge data are matched from a working condition database, the cooling liquid circulation rate is adjusted, an auxiliary heat dissipation mechanism is activated, and an environment adaptation type heat dissipation mode is generated. The heat dissipation efficiency of the charging pile is improved, precise temperature control is achieved, and therefore safe and stable operation of the charging pile is guaranteed.

The invention relates to the technical field of air conditioner energy-saving control, in particular to an evaporation cooling air conditioner energy-saving optimization control method based on deep reinforcement learning, and the method comprises the steps: calculating a heat load rising index according to the change trend and change amplitude of the environment temperature in the local time period of each moment in the operation process of an evaporation cooling air conditioner; obtaining an energy consumption peak value synchronization index according to the similarity degree of peak value fluctuation in the power of the fan, the water pump and the evaporator in the local time period of each moment; calculating the environmental complexity according to the difference between the thermal load rising index and the energy consumption peak value synchronization index at each moment; setting a reward function in a deep reinforcement learning algorithm by integrating the environment temperature and the environment complexity at each moment; and according to the environment temperature and the power of the water pump and the evaporator at the current moment, the deep reinforcement learning algorithm is used for conducting optimization control on the fan power of the evaporative cooling air conditioner. According to the method, the precision of air conditioner energy-saving control by using a deep reinforcement learning algorithm can be improved.