1585 results about "Water chiller" 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 discloses an energy-saving control method and system for a water chilling unit, and relates to the technical field of energy-saving control. During operation of the system, a data set is synchronously collected from a water chilling unit system through a multi-channel asynchronous sampling mechanism, time sequence compression and redundancy removal are carried out, an embedded perturbation calculation mechanism is used for calculating and generating a non-dominant control core coefficient, and the non-dominant control core coefficient is used for controlling the energy-saving control of the water chilling unit; a three-dimensional coefficient space is converted and output through an entropy state change structure and is used for constructing a state balance atlas, comprehensively calculating a control state index SEEI, evaluating the current energy state offset degree of a system, determining whether intervention is carried out or not, carrying out rule search and nonlinear modeling based on the control state index SEEI value, generating an adjustment matrix, and carrying out state balance analysis. And starting a data reconstruction micro-strategy of a short-time historical window, receiving an adjustment matrix, converting the adjustment matrix into a device-level instruction, executing an action through an edge controller, feeding back a response error epsilon (t) in real time, and predicting a potential performance degradation trend based on long-time system operation data.

The invention discloses an intelligent air conditioner water chilling unit control method and system based on predictive optimization. Operation data and weather forecast data are collected to establish a dynamic response reference, building cold load sudden change opportunity is recognized, the mismatching relation between magnetic suspension frequency and wet bulb temperature is detected, and energy-saving opportunity recognition data is generated to determine a cooling starting judgment table; identifying equipment response delay characteristics by using a dynamic response reference, extracting time sequence advantage parameters to determine dislocation configuration among multiple pieces of equipment, and generating coordination control parameters; cloud-local transmission delay analysis is carried out according to the coordination control parameters, and a coordination control sequence is generated through buffer opportunity identification and delay compensation; mechanical refrigeration suppression data is generated through energy efficiency mode classification, free cooling potential mining is implemented to form a cold source optimization factor, and an emergency response strategy is generated; an emergency response strategy is used to identify a multi-device linkage trigger critical zone, a prediction correction feedback network is constructed, a global collaborative optimization instruction is generated, and the system operation efficiency and the control precision are improved.

The invention provides a high-efficiency control method and system for a central air conditioner refrigeration machine room, and relates to the technical field of automatic control, and the method comprises the steps: 1, obtaining chilled water supply and return water temperature difference and flow data, and calculating the dynamic cold load demand of a building in combination with the personnel distribution thermal imaging data of each floor; and 2, on the basis of the dynamic cooling load requirement, a dynamic adjustment model for the number of running water chilling units is built, matching degree calculation is conducted on the actual cooling load value and the single refrigerating capacity of the water chilling units through a fuzzy PID control algorithm, and a final unit running combination scheme is generated. By calculating the cooling load requirement, dynamically adjusting the operation parameters of the water chilling unit, the chilled water pump and the cooling tower and balancing the equipment operation time, the system energy efficiency is effectively improved, the energy consumption and the operation and maintenance cost are reduced, and stable operation of the refrigerating system is guaranteed.

The invention relates to the technical field of non-electrical variable control, and discloses an industrial water chiller temperature intelligent adjusting system, which comprises a refrigeration circulation loop and a control unit, the control unit calculates a steady state control component based on the water outlet temperature deviation, performs differential processing on the refrigerant pressure to extract the gradient, and outputs the gradient. Generating a transient compensation component when the gradient exceeds a dynamic noise threshold; according to the method, the problem of thermal lag is solved by utilizing the pressure wave transmission speed advantage, aggressive response is prevented from triggering low-pressure shutdown through a safety margin constraint mechanism, the pressure safety margin is calculated in real time, a gain coefficient is determined according to a nonlinear model, and a final driving instruction is generated. And the dynamic balance of the control response speed and the system physical security boundary is realized.

The invention relates to the field of factory intelligent cooling, and discloses an MPC-based large factory intelligent cooling system and a cooling control method, the system comprises a data acquisition module, an AI control module, a cooling tower control module, a cooling water pump control module and a cooling-water machine control module; the data acquisition module acquires outdoor environment temperature and humidity, cooling tower outlet water temperature, cooling water pump inlet and outlet water temperature difference and flow and water chiller operation state data in real time. The AI control module constructs a system model through real-time data, predicts and optimizes by using an MPC algorithm, and calculates optimal values of the running frequency of a cooling tower fan, the running frequency of a cooling water pump and the power of a cooling-water machine compressor by adopting sequential quadratic programming, so as to realize cooperative dynamic control of equipment in the system; the overall operation efficiency of the cooling system under the outdoor temperature and humidity change condition is effectively improved, and the overall energy consumption of the system is minimized in real time.

The invention relates to the technical field of intelligent control, in particular to an inspection system and method for a heating and ventilation system based on a knowledge graph, and the system comprises a feature extraction module, a graph construction module, an anomaly tracing module, a causal analysis module and a priority module. According to the method, the inlet and outlet water temperature and flow data of the water chilling unit are collected, deviation characteristics are extracted in combination with principal component analysis, the operation state is quantified, an embedded map participates in state judgment, the anomaly detection capacity is improved, initial anomaly and upstream nodes are focused, the analysis range is narrowed, and causal tracing is carried out based on the state influence between devices; by means of a Bayesian network, a state evolution chain is constructed, a time sequence and an inter-structure fault are bridged, task priority is evaluated according to a link starting point and length, equipment dynamic sorting and state updating are carried out, inspection scheduling accuracy and efficiency are improved, and a closed-loop process which is high in recognition accuracy, small in analysis boundary, clear in path and excellent in resource allocation is formed.

The invention provides a system-level collaborative water-cooling energy-saving control device and method based on AI fusion refrigeration, and the device comprises an edge calculation unit which is used for receiving the operation working condition parameters, the output working condition and refrigerating capacity prediction information of a refrigeration system, and a water-cooling system control strategy; the cooperative control unit is used for receiving the control strategy pushed by the edge computing unit and performing cooperative control on each device of the water cooling system; the collecting unit is used for collecting operation parameters of the refrigerating system. By establishing the complete system energy consumption model and the multi-constraint optimization algorithm, global optimization control over equipment such as a water chilling unit, a water pump and a cooling tower is achieved.

The invention provides a water chiller predictive maintenance method and system based on digital twinning, and the method comprises the steps: obtaining the evaporation pressure, suction temperature, refrigerant flow and outlet water temperature parameters during the operation of a main module of a water chiller, and carrying out the synchronous collection through multiple sensors, thereby forming a time series data set; according to the time sequence data set, a sliding window method is adopted to extract the mean shift amount, variance volatility and cross correlation coefficient of evaporation pressure and suction temperature, and a collaborative drift mode reflecting micro leakage is obtained; according to the corrected drift rate and cross correlation coefficient, generating a feature vector of a collaborative change direction among the evaporation pressure, the suction temperature and the refrigerant flow; and by calculating the Euclidean distance between the feature vector of the cooperative change direction and the health baseline, whether the micro leakage reaches the early warning triggering degree is judged, and the strength of an early warning signal is obtained.

The invention provides a water chilling unit performance prediction method based on an improved physical information neural network. The method comprises the following steps: step 10, constructing a neural network model; step 20, selecting to obtain a neuron variable, and embedding the neuron variable into the neural network model as a physical neuron to obtain a physical neuron embedded physical information neural network model; step 30, introducing a loss function into the physical neuron embedded physical information neural network model; 40, carrying out data balance processing on the original data set, and screening to obtain a training set; step 50, utilizing the training set to train the physical neuron embedded physical information neural network model to obtain a water chilling unit performance prediction model; and step 60, predicting the performance of the water chilling unit by using the water chilling unit performance prediction model. According to the improved water chilling unit performance prediction method based on the physical information neural network, high-precision prediction of the performance of the water chilling unit is achieved, and the generalization ability and the model interpretability are improved.

The invention relates to a data center equipment type selection method based on electrical and heating ventilation load linkage, and belongs to the technical field of data center infrastructure design. The model selection method comprises the steps of setting basic data, obtaining the number of machine rooms and the number of IT devices in a single machine room, obtaining the total power of the IT devices, setting an energy efficiency index set value, obtaining the project power consumption scale, obtaining the total cooling load, selecting models of air conditioners at the tail ends of the machine rooms and substations, selecting models of water chilling units, selecting models of heat exchangers, selecting models of cooling water pumps and chilled water pumps and selecting models of cooling towers. And obtaining the total power of the air conditioner, obtaining an energy efficiency index accounting value, and carrying out PUE verification. According to the method, through closed-loop iteration of electrical load-heating and ventilation load-PUE, model selection and quantity selection of all key equipment are completed at a time; professional splitting, repeated adjustment and modification and capacity redundancy caused by traditional serial design are avoided, the design period is remarkably shortened, and initial investment is reduced.

The invention relates to an urban rail transit station ventilation and air conditioning system cooperative control method, device and equipment based on dynamic energy efficiency optimization and a medium. Constructing an energy efficiency model of the ventilation and air conditioning system by combining the energy efficiency curved surface characteristics of the water chilling unit and the cubic law power consumption characteristics of the frequency conversion equipment; an intelligent optimization algorithm is adopted, a dynamic scaling temperature feasible domain of chilled water of a water chilling unit and a frequency interaction limitation domain of frequency conversion equipment are constructed, the feasibility of a temperature set value is kept, meanwhile, coupling constraints in the frequency conversion equipment are decoupled, and an optimal parameter combination is solved; and the optimal parameter combination is issued to an execution layer, the actual energy efficiency ratio deviation of the system is monitored in real time, and energy efficiency model parameter re-calibration or iterative optimization is triggered according to a deviation threshold. Therefore, the overall energy efficiency of the ventilation air conditioning system is stably improved, and efficient operation under the dynamic working condition is achieved.

The invention relates to the technical field of power generation system transformation, in particular to an energy storage power generation system and method based on thermal power plant transformation. The Carnot battery unit comprises a liquid carbon dioxide storage tank, an electric heater, a compressor, a heat storage transducer heat flow channel and an expansion machine which are connected in sequence, and the liquid carbon dioxide storage tank adopts a boiler drum of a thermal power plant and stores liquid carbon dioxide liquefied by a water chilling unit of the thermal power plant; the heat storage circulating unit exchanges heat with a heat flow channel of the heat storage transducer to store heat; the steam power generation unit adopts a thermal power plant steam generator set and extracts heat stored by the heat storage circulation unit for steam power generation. The thermal power generating unit is transformed into the carbon dioxide Carnot battery energy storage system, the defect that a power grid is unstable in the process that a traditional thermal power plant is gradually converted into new energy is overcome, double stable output electric quantity is achieved, the system efficiency is improved, and meanwhile high economic benefits are achieved.

The utility model discloses a multi-system water chilling unit which comprises at least two heat exchange systems, at least two waterway systems and a combined heat exchanger, and the heat exchange systems can be combined to form or respectively form an independent heat exchange circulation loop by switching the serial or parallel connection state and the opening or closing state of the combined heat exchanger; the water path system can be combined to form or respectively form an independent water circulation loop, so that the heating or refrigerating capacity of the unit is obviously increased; different heat exchange circulation loops are switched and controlled by adjusting refrigerant flowing paths between the multiple heat exchange systems and the combined heat exchanger, and different water circulation loops are switched and controlled by adjusting water medium flowing paths of the multiple water path systems. Therefore, after the water chilling unit is installed, different operation modes can be selected and switched according to different heat or cooling capacity requirements, hot water or cold water with the corresponding capacity and temperature is produced, the heating or cooling capacity of the unit is matched with the actual requirement, the whole equipment or part of elements do not need to be replaced, cost is low, and maintenance is convenient.

The invention belongs to the technical field of storage and charging equipment, and particularly relates to a storage and charging all-in-one machine which comprises a shell cooling mechanism, the interior of a shell is divided into a battery bin and an inversion bin, a battery module is arranged in the battery bin and comprises a plurality of stacked battery cells, an alternating-current and direct-current inverter is arranged in the inversion bin, and the battery cells are connected with the alternating-current and direct-current inverter. And the AC / DC inverter is electrically connected with the battery module. According to the invention, a closed-loop liquid cooling circulation system is adopted, heat conduction liquid can rapidly take away heat when the battery cell works, performance degradation or potential safety hazards of the battery cell caused by too high temperature are avoided, the heat dissipation area is increased through the design of the circuitous and surrounding insulating heat conduction pipe, and the cooling efficiency is obviously higher than that of a traditional air cooling scheme in cooperation with constant temperature control of the industrial water cooler. The shell is divided into the battery bin and the inverter bin, the battery module and the alternating current and direct current inverter are arranged in a partitioned mode, mutual interference of heat generated when the battery and the inverter work can be properly avoided, maintenance of all parts is facilitated, and the operation stability of equipment is improved.

The invention relates to the technical field of printing equipment, in particular to a printing ink drying device for anti-counterfeiting stained paper, which comprises a rack, a conveying mechanism is arranged above the rack, a drying box body is arranged above the conveying mechanism, and the drying box body is sequentially divided into a leveling preheating area, a main curing area and a forced cooling area along the conveying direction; the conveying mechanism comprises a high-temperature-resistant conveying mesh belt and a vacuum adsorption platform arranged below the mesh belt; an LED-UV cold light source assembly is arranged in the main curing area, infrared heating pipes transversely arranged in the leveling preheating area and a reflecting cover above the infrared heating pipes are matched with the LED-UV cold light source assembly with a water-cooling circulation flow channel in the main curing area and an external cooling-water machine, and printing ink is evenly heated through infrared radiation to be leveled firstly; curing is completed through low-temperature ultraviolet light, a light source is cooled synchronously in a circulating mode, the effects of ink flat curing and paper low-heat deformation are achieved synchronously, and high-speed continuous operation is effectively supported.

The invention relates to the technical field of general control systems, in particular to a water chilling unit energy-saving control method and system.The method comprises the steps that the machining process of a numerical control machine tool is equally divided into a plurality of monitoring time periods, and the demand degree of a water chilling unit in the machining process of the numerical control machine tool in the monitoring time periods is determined to screen out a target monitoring time period; energy consumption of the water chilling unit in the target monitoring time period is determined in combination with the time interval from the moment after the cutting temperature rises to the moment when the rotating speed of the compressor changes, and then the cooling effect of the water chilling unit in the target monitoring time period is determined in combination with rising changes of the cutting temperature and the environment temperature. And determining a regulation and control coefficient of the variable frequency driving control system in the target monitoring time period, and regulating and controlling the running speed of a compressor of the water chilling unit. The regulation and control coefficient for energy-saving control of the water chilling unit in the frequency conversion control system is obtained, and the operation speed of the compressor of the water chilling unit is regulated and controlled, so that the purpose of energy-saving control of the water chilling unit is achieved.

The invention relates to the field of equipment control, in particular to an equipment energy-saving control system and method based on an AI large model, and the system comprises an equipment sensing module, a load prediction module, a fuzzy control module, a wind-water joint debugging module and an energy efficiency optimization module, the equipment sensing module is used for determining the thermal gain in a region, the load prediction module is used for generating a pre-control decision, and the fuzzy control module is used for generating a fuzzy control result; the fuzzy control module is used for calculating static pressure and air supply volume, the air-water joint debugging module is used for correcting the air supply volume of each area, and the energy efficiency optimization module is used for planning the refrigerating capacity supply efficiency of the air conditioner in different time periods. The stable operation of equipment such as an air-conditioning compressor, a water pump and a fan is guaranteed; the reliability of an energy-saving control system is enhanced; the energy consumption cost of building operation is reduced; and the comprehensive energy efficiency of an air-conditioning system is improved.

The utility model relates to an oil-fluorine separator of a marine water chilling unit. A condenser is connected with a coil exhaust heating interface of the oil-fluorine separator through a high-pressure gaseous refrigerant pipeline, and is connected with an exhaust interface of the oil-fluorine separator through the high-pressure gaseous refrigerant pipeline and a high-pressure exhaust electromagnetic valve; an air suction interface of the oil-fluorine separator is connected with the evaporator through a low-pressure air suction electromagnetic valve and a low-pressure gaseous refrigerant pipeline; a low-pressure gas outlet connector of the oil-fluorine separator is connected with the evaporator through a low-pressure gaseous refrigerant pipeline; the evaporator is connected with a liquid inlet interface of the oil-fluorine separator through an oil-fluorine mixture pipeline and a low-pressure liquid inlet electromagnetic valve; an oil outlet connector of the oil-fluorine separator is connected with an oil tank through a lubricating oil pipeline via a one-way valve; the electrical control box is connected with the high-pressure exhaust electromagnetic valve, the low-pressure air suction electromagnetic valve and the low-pressure liquid inlet electromagnetic valve through signal lines. The oil-fluorine separation device can be used for separating the oil-fluorine mixture on the liquid surface of the flooded evaporator, and the heat exchange effect of the flooded evaporator is improved.

The invention discloses a water chilling unit operating under extreme working conditions, which comprises a fan and a finned condenser at the upper part and a refrigerating unit at the lower part, and the refrigerating unit is provided with a refrigerant circulating system and a chilled water circulating system; the refrigerant circulating system comprises a compressor, a finned condenser, an electronic expansion valve and a shell and tube evaporator which are connected in sequence; the chilled water circulation system comprises a water pipe, a water pump and an evaporator which are connected in sequence; the electronic expansion valve is connected with the drying filter cartridge and the shell and tube evaporator, the drying filter cartridge is connected with the liquid storage tank, and the shell and tube evaporator is connected with the gas-liquid separator. According to the invention, PWM and stepless regulation multi-dimensional cooperative control are used, so that stable operation is realized when the energy efficiency in a wide temperature range is suddenly reduced; on the high-temperature side, the condensation fan adopts a stepless speed regulation technology; and the low-temperature side is switched into a PWM period adjusting mode.

The invention provides a wind-water linkage energy-saving control system for an urban rail transit underground station. The wind-water linkage energy-saving control system comprises a management layer; the control layer is divided into three relatively independent and expandable cooperative control subsystems capable of independently acquiring information according to the type of equipment, the control layer comprises a large system cooperative control subsystem, a small system cooperative control subsystem and a water system cooperative control subsystem, and the cooperative control among the cooperative control subsystems is completed by the management layer platform; a control strategy of the urban rail transit underground station wind-water linkage energy-saving control system comprises a system calendar scheduling strategy; a system control strategy; comprising a large system air conditioner adding strategy, a large system air conditioner reducing strategy, a water system starting working condition setting strategy, a water system operation working condition switching strategy, a cooling water temperature difference optimization setting strategy, a chilled water temperature difference optimization setting strategy, a most unfavorable tail end pressure difference setting strategy, a most unfavorable tail end pressure difference control strategy and a water chilling unit adding strategy. A water chilling unit reduction strategy, a water chilling unit alternation strategy and a water chilling unit operation load balancing strategy; and the system cooperative control comprises one-key startup of the water chilling machine room, one-key shutdown of the water chilling machine room, one-key startup of the water chilling unit, one-key shutdown of the water chilling unit, automatic addition of the water chilling unit and automatic reduction of the water chilling unit.

Disclosed herein are compositions comprising HFO-1252zc and at least one compound selected from the group consisting of HFO-1132E, HFC-32, HFC-134, CF3I, and CO2. The compositions are useful in refrigeration, air conditioning, heat pumps and chillers for cooling, heating or replacing other refrigerants.

The invention relates to the field of electric power systems, in particular to an energy storage dynamic optimization scheduling method and system of an electric power system and a storage medium, and the method comprises the steps: S1, building an energy storage dynamic calculation model; s3, energy consumption models of a water chilling unit, an air source heat pump, a water pump and a cooling tower are established respectively, and instantaneous energy consumption under different working conditions is calculated by considering operation working conditions and environmental parameter correction; and S4, outputting the utilization rate, the maximum adjusting power, the average adjusting power, the maximum adjusting capacity proportion and the accumulative adjusting electric quantity proportion of the energy storage device, and carrying out quantitative evaluation. According to the method, supply and demand state changes such as valley load, flat load, peak load, peak load and the like of the power system can be identified in real time / quasi-real time, the time periods and power of energy storage and energy release are adjusted, dynamic power distribution of a host in each load time period is realized, and the overall energy efficiency level and operation stability of the system are improved.

The invention is suitable for the field of air conditioners, and discloses an energy-saving and cost-saving air conditioning system and a control method. The system comprises a meteorological sensor, an automatic control device, an outdoor cooling device, a water chilling unit, a cold storage device, indoor end equipment, a first electric valve, a second electric valve, a third electric valve, a fourth electric valve, a fifth electric valve, a sixth electric valve, a cold water discharging pump, a first temperature sensor and a second temperature sensor, the outdoor cooling device is connected with the water chilling unit, the water chilling unit is connected with the cold storage device and the indoor end equipment, the cold storage device is connected with the indoor end equipment, the system utilizes the characteristic that the peak-valley electricity price at night is low, the cold storage mode is operated in the low-electricity-price period, the cold storage device is preferentially used for cooling in the high-electricity-price period, and the electric charge expenditure can be reduced.

The utility model relates to the technical field of cold storage and energy storage, and provides a chilled water storage refrigerating system. Comprising an energy storage pool, a heat exchanger assembly and a water chilling unit. The energy storage pool is connected with the cold release side of the heat exchanger assembly to form a circulation loop. The user side of the heat exchanger assembly is connected with the user side to form a circulation loop. The chilled water side of the water chilling unit is connected with the energy storage pool to form a circulation loop, and the chilled water side of the water chilling unit is connected with the user side to form a circulation loop; the cooling water side of the water chilling unit is connected with the cooling tower assembly to form a circulation loop. The water chilling unit has the beneficial effects that the water chilling unit stores energy for the fire-fighting energy storage water pool and / or the newly-built energy storage water pool in the electricity utilization trough period at night, and the stored energy in the fire-fighting energy storage water pool and / or the newly-built energy storage water pool exchanges heat with the heat exchanger assembly to refrigerate the user side in the peak period and the peak period in the daytime; after the stored energy in the fire-fighting energy storage water pool and / or the newly-built energy storage water pool is used up, the water chilling unit and the user side are used for heat exchange refrigeration, and the refrigeration cost is reduced.

The invention relates to the technical field of precise temperature control, and discloses a liquid level temperature control system of an industrial water chiller, which comprises a liquid level adjusting loop, a temperature adjusting loop and a cooperative control device with a one-way logic channel, and calling a preset flow mapping model to check a mass flow estimated value, calculating an instantaneous enthalpy flow change rate introduced by a water supplementing action, converting the instantaneous enthalpy flow change rate into a feedforward compensation signal, superposing the feedforward compensation signal to a temperature adjusting loop, and executing model parameter self-calibration logic based on thermal response residual. Zero time difference immunization on water replenishing thermal disturbance is realized; meanwhile, flow model parameters are reversely corrected through temperature residual errors, and the adaptive capacity of the system for resisting water pressure fluctuation and assembly aging under the flowmeter-free working condition is improved.

Disclosed herein is a system for controlling a chilled water plant comprising one or more chillers, one or more water pumps, and a controller. The system comprise one or more processors configured to receive information comprising historical data for a plurality of system variables for the chilled water plant; determine historical performance information for the chilled water plant; prepare performance models comprising: at least one chiller predictive model; and at least one pump predictive model; prepare a field load predictive model for a field load demand; prepare a chilled water plant model; simulate operation of the chilled water plant and determining first optimised control parameters for the chilled water plant; determine an energy consumption of the chilled water plant; determine optimised control parameters for the chilled water plant; and output the optimised control parameters to the controller of the chilled water plant to optimise control of the chilled water plant.

This application provides a device, system and method for predicting and calculating energy consumption of a chiller unit. The system and method includes: a chiller unit load prediction step of predicting and outputting a total load of the chiller unit based on a preset cooling load prediction model; a chiller load distribution step of distributing the total load of the chiller unit to generate a first chiller load and a second chiller load, according to a chiller load distribution logic; a chiller energy efficiency value acquisition step of correspondingly acquiring a first chiller energy efficiency value and a second chiller energy efficiency value according to a chiller load-energy efficiency relationship; and a chiller power calculation step of calculating a first chiller input power and a second chiller input power according to the first chiller energy efficiency value and the second chiller energy efficiency value.

The invention discloses an efficient refrigerating machine room energy-saving automatic control system based on reinforcement learning, and the system comprises the following modules: an operation data collection module which is used for collecting key equipment operation parameters and generating unified time sequence data; the energy consumption modeling module constructs energy consumption mathematical models of the water chilling unit, a water pump and a cooling tower and stores the energy consumption mathematical models into a database; the cooling capacity prediction module is used for predicting the future cooling capacity demand based on the historical data and the environmental parameters; the feed-forward optimization module is used for optimizing power distribution by using an adaptive particle swarm algorithm and generating control parameters; the state correction module automatically adjusts the running state according to the running efficiency deviation condition; the cooling strategy optimization module introduces an improved DSAC algorithm to optimize a cooling control strategy; and the instruction deployment module deploys the strategy to an actual system and outputs a regulation and control instruction. The energy efficiency management level of the refrigerating machine room is improved, and integration of energy conservation and intelligent control is achieved.

The invention relates to the technical field of water chilling unit control, in particular to a multi-connected control system for a low-temperature cascade water chilling unit. The system comprises a data acquisition module used for acquiring historical and real-time refrigeration parameter sequences; the refrigeration demand analysis module screens an abnormal period based on the volatility of different period parameter sequences, and calculates a historical refrigeration demand degree in combination with normal period data; the adjustment degree analysis module identifies abnormal units through parameter deviation and gives an alarm, non-abnormal units are sorted according to the parameter deviation degree to generate a demand sequence, and the pressure adjustment degree of the units is dynamically calculated in combination with liquid level distribution; and the adjustment control module performs pressure control on the unit according to the demand sequence and the pressure adjustment degree. According to the method, the historical data and the real-time parameters are fused, the abnormity is responded in time, the unit pressure is dynamically adjusted, the influence of the abnormal unit on the cooperative operation stability of the multiple units under the complex condition is reduced, and the refrigeration effect of the low-temperature refrigeration system meets the high reliability requirement.