45 results about "Specific energy consumption" patented technology

The invention discloses a railway engineering mechanical equipment energy consumption digital monitoring method and system, and relates to the field of railway construction equipment energy consumption management, and the method comprises the steps: obtaining the energy consumption data of each piece of to-be-selected railway engineering mechanical equipment in the operation process; preprocessing the energy consumption data in an edge processing unit to obtain a standardized feature vector; on the basis of the feature vectors, through a working condition recognition model, recognizing the current working condition of each piece of to-be-selected railway engineering mechanical equipment, and generating a working state labeling sequence; before operation task scheduling, unit energy consumption of each piece of to-be-selected railway engineering mechanical equipment is predicted based on the three-dimensional coupling atlas and the target task type, and task allocation optimization suggestions are output; and determining target railway engineering mechanical equipment based on the task allocation optimization suggestion, and outputting control parameters of the target railway engineering mechanical equipment. The key problems of energy consumption monitoring lag, working condition identification difficulty, unreasonable multi-equipment task allocation and the like in the prior art are effectively solved.

The invention relates to a large model energy consumption optimization method and device, computer equipment, a computer readable storage medium and a computer program product. Comprising the steps of collecting hardware state data and task data of a large model; performing stage identification according to the task data, and determining a current stage; performing state prediction according to the hardware state data and the task data through a prediction model corresponding to the current stage to obtain target state information; generating optimization parameters of the current stage through a joint optimizer according to the target state information; and adjusting the resources of the large model according to the optimization parameters. In combination with stage perception and dynamic resource adjustment, a differentiated resource adjustment strategy based on different stages is realized, specific energy consumption pain points in an AI scene are solved, high power consumption of large model training, instantaneous fluctuation of reasoning requests and the like are reduced, sustainable and efficient operation of an AI system is ensured, the computing power demand and resource consumption of a large model are balanced, and the system performance is improved. And wide landing and development of a large model in various scenes are facilitated.

The invention discloses a vertical ultrafine grinder, aiming at solving the technical problems that the productivity of the vertical ultrafine grinder can be improved and the marginal decreasing effect of unit energy consumption can be effectively overcome. Comprising a smashing chamber, a smashing disc located in the smashing chamber, a smashing disc rotation driving mechanism in transmission connection with the smashing disc, a feeding structure, a discharging structure and an air inlet structure, and the feeding structure, the discharging structure and the air inlet structure are communicated with the smashing chamber. The diameter of the smashing disc ranges from 1950 mm to 2050 mm, the edge linear speed ranges from 160 m / s to 170 m / s when the smashing disc works, and the rated power of the smashing disc rotation driving mechanism ranges from 230 kW to 270 kW. And the unit energy consumption rebound trend is successfully improved while the productivity is remarkably improved.

The invention relates to the technical field of cable production and manufacturing and automation control, in particular to an energy-saving cable extrusion production process control system, which comprises a data acquisition module for acquiring real-time working condition parameters of an extrusion production line; the rheological thermal coupling analysis module is used for resolving the shear heat contribution rate under the current working condition; the heat engine response decoupling module is used for determining a heat engine response lag time difference between mechanical shear heat and machine barrel heat conduction; the energy efficiency optimization calculation module is configured to generate a dynamic heat balance control strategy aiming at an unsteady state working condition according to the heat engine response lag time difference and a preset unit output ratio energy consumption target; the self-adaptive execution module is configured to output a cooperative control instruction for a heating and cooling system and a screw driving system based on the dynamic heat balance control strategy so as to realize minimization of system energy consumption; according to the method, the common energy confrontation phenomenon of alternate operation of heating and cooling in traditional control is solved, and the energy consumption in the transition process is greatly reduced.

The application discloses a driving behavior influence on energy consumption evaluation method, system, vehicle and equipment. Wherein, the driving behavior influence on energy consumption evaluation method comprises: obtaining driving data of a vehicle; obtaining driving behavior characteristic data according to the driving data; taking unit energy consumption of the vehicle as a target variable and taking the driving behavior characteristic data as an input variable, a regression analysis model between the driving behavior and the unit energy consumption is constructed, wherein the regression analysis model represents the influence relationship of different driving behaviors on the energy consumption of the vehicle; according to the parameters of the regression analysis model, the energy consumption influence weight corresponding to each type of driving behavior characteristic data is calculated, and the influence of the driving behavior on the energy consumption is evaluated according to the energy consumption influence weight. By analyzing the influence of the driving behavior on the energy consumption of the vehicle, the driving habit, the loading configuration and the driving route can be optimized, and the energy consumption and the carbon emission can be significantly reduced.

The application discloses an automatic material discharging device and relates to the material transportation technical field.The automatic material discharging device comprises a rack assembly and a hopper assembly.The hopper assembly is movably connected to the rack through an elastic deformation recovery mechanism.The recovery mechanism can drive the hopper assembly to reciprocate between a material receiving position and a material discharging position in the vertical direction.A limiting device is arranged at the material receiving position to limit the movement of the hopper assembly.The automatic material discharging device can accurately place the material package on the target position, and the material package is lowered by gravity.The hopper is opened through a self-locking mechanism, so that the unit energy consumption and the equipment cost can be reduced.

The invention relates to a cutting rock-breaking mechanism and a cutting method, and the cutting rock-breaking mechanism comprises a cutter assembly which comprises a sun gear rotating around a first axis; the planet gears are arranged at intervals in the circumferential direction, and eccentric structures are arranged on the planet gears; the planet wheel mandrel is sleeved with the planet wheel and rotationally connected with the planet wheel so as to bear inertia moment and / or radial inertia force which alternately rotates around the first axis; the planet carrier is coaxial with the first axis and is fixedly connected with the planet wheel mandrel; the cutterhead frame is connected with the planet carrier; when the planet carrier alternately rotates around the first axis, the cutter head frame reciprocates along the first axis and / or alternately rotates around the first axis; when the planet carrier swings in the radial direction, the cutterhead frame swings in the radial direction in a rotating mode. And the cutter is fixedly connected with the cutter head frame and has an eccentric distance. Rock is cut and broken under the multiple actions of extrusion feeding force of the cutter, vibration impact of the cutter and radial eccentric impact rock breaking, so that the rock breaking capacity (productivity) and the rock breaking efficiency are improved, the specific energy consumption of rock breaking is reduced, and the cutter is suitable for breaking hard rock.

Energy consumption warning procedure, the procedure comprehensive: Measuring location-specific energy consumption values ​​(121) over a specific period of time at a sensor (170) that is deployed at a location of a monitored site; Decomposition of the location-specific energy consumption values ​​(121) according to a first characteristic, wherein the energy consumption values ​​(121) are decomposed by performing a date-based decomposition type; Decomposition of the location-specific energy consumption values ​​(121) according to a second characteristic comprising: Decomposition of the energy consumption values ​​(121) by performing a seasonal decomposition into the components: trend, season, and remainder, to identify changes in energy consumption that are due to seasonal effects, and to identify changes that are due to a general trend; Obtaining an initial decomposed energy consumption value (123) based on the first characteristic and based on the residual component to identify any change in energy consumption that is due to unintentional energy consumption; Determining a corresponding first reference value based on the decomposed values ​​(123); Comparing the first, decomposed energy consumption value (123) with the determined first reference value; Outputting a message to notify a user of unintended energy consumption if the first decomposed energy consumption value (123) and the determined first reference value are different.

The utility model relates to the technical field of nitryl mother liquor recovery and energy conservation, in particular to a high-concentration nitryl mother liquor recovery and energy conservation device. Comprising a supporting cylinder, a supporting beam is arranged on the top face of a supporting cylinder body, a motor is arranged on the supporting beam, an output shaft of a motor body is connected with a shaft rod, the shaft rod is located in an inner cavity of the reaction kettle, and the inner cavity of the supporting cylinder body is sleeved with a reaction kettle body; a scraping plate is fixedly arranged on the shaft rod body, a plurality of teeth are arranged on the outer side surface of the scraping plate body, and the teeth are used for scraping mixed scale on the inner wall of the reaction kettle; the cleaning efficiency of the teeth on inner wall polymer scaling is improved, the temperature difference stability is improved, the recycling value of the teeth as a low-grade heat source is increased, the evaporation time is shortened, unit energy consumption is reduced, and the energy utilization rate and economic benefits of multi-effect evaporation are improved.

The utility model discloses a kind of unit energy consumption uses online monitoring device, including monitoring box, the lower end in monitoring box is equipped with monitoring equipment protection shell, the monitoring equipment protection shell is boat type structure, recess is equipped between the monitoring equipment protection shell and monitoring box, the upper end of monitoring equipment protection shell extends device recess, fixed mechanism is equipped in the recess, the lower end of monitoring box is equipped with article slot, servo motor is fixedly connected in the article slot, the output shaft end of servo motor is fixedly connected with rotating rod, the end of rotating rod away from servo motor is rotatably connected with article slot inner side wall. The unit energy consumption uses online monitoring device when online monitoring can be adjusted in multiple angles multidirection, realizes unit energy consumption comprehensive monitoring, improves the accuracy of unit energy consumption monitoring result.

The present application relates to solid waste resource utilization technical field, specifically disclose a kind of solid alternative fuel based on gasification fine slag, by weight parts, including gasification fine slag 10~40 parts, municipal sludge 10~40 parts, byproduct of citrus fruit 30~70 parts, the forming density of the solid alternative fuel is 1.28g / cm 3 , compressive strength is 1.22N / cm 2 And specific energy consumption is 10.65J / g.The specific preparation process includes the following steps: 1) pretreatment is carried out to raw material respectively;2) the pretreated raw material is mixed;3) the mixed raw material is added to granulating equipment and extruded into smooth cylindrical solid alternative fuel.The present application is based on gasification fine slag, adds municipal sludge and biomass to obtain solid alternative fuel, improves the defect that gasification fine slag combustion heat value is not high, and can reduce ash content, so that it meets the conditions of resource utilization, with higher density and compressive strength, facilitate the solid alternative fuel as fuel product transportation and preservation, provide new technical ideas and direction for the use of gasification fine slag.

The invention relates to the technical field of intelligent control of grease processing equipment, in particular to a temperature self-adaptive control method of rapeseed oil squeezing equipment. Comprising the following steps: a data acquisition step: calculating a first-order derivative of real-time temperature with respect to time to obtain a temperature change rate; an observer construction step: constructing a dynamic friction heat flow observation model, and calculating the rheological impedance coefficient of the material at the current moment; a space mapping step: mapping the rheological impedance coefficient to a preset two-dimensional energy efficiency phase plane, and calculating a normal deviation between the current working condition point and a preset optimal energy efficiency manifold trajectory; a closed-loop control step: driving the current working condition point to evolve along the optimal energy efficiency manifold trajectory based on the normal deviation; according to the method, the limitation that traditional control only depends on single temperature feedback is broken through, blind work of a motor in a low-efficiency interval is avoided by constructing an extrusion efficiency-heat dissipation rate two-dimensional energy efficiency phase plane, and the physical extrusion effect is maximized while unit energy consumption is reduced.

The invention discloses a cutterhead arrangement method for improving TBM (tunnel boring machine) hob tunneling efficiency in extremely hard rock tunneling, which is characterized in that two rows of first multi-blade hobs, two rows of second single-blade hobs and two rows of side hobs are arranged on a cutterhead at intervals, the end faces of the blades of the first multi-blade hobs are higher than the end faces of the blades of the second single-blade hobs, and the first multi-blade hobs and the second single-blade hobs are arranged at intervals; the rear single-blade hobs are annularly arranged between the two rows of the front multi-blade hobs in the radial direction, the side hobs are arranged on the cutterhead excavation boundary arc lines on the outermost sides of the two rows of the front multi-blade hobs and adopt single blades, and by means of the arrangement method, specific energy consumption needed by rock breaking in unit volume is remarkably reduced, the economical efficiency and construction efficiency of TBM tunneling are improved, and the construction cost is reduced. The method is suitable for hard rock breaking scenes such as tunneling, mining and deep rock mass engineering.

The invention relates to a wheel-rail traction large web plate whole machine flying load separation electricity and water cooling cogeneration flying path system, in particular to a train rail path system provided with a groove splicing whole path wheel-rail traction large web plate air lubrication and magnetic suspension roller shaft, which comprises a large web plate dragged by a wheel rail on an air bearing suspension roller shaft road surface, and the web plate is connected into an odd-length train in a hanging mode. The flight path is provided with four to a plurality of layers on the viaduct, the upper path and the lower path are oppositely opened in a one-way reciprocation manner, and the total energy-saving unit energy consumption ratio is less than 0.6; the flight path system is safe, green, service, order, fairness, sharing, rapidness, high efficiency, energy saving and the like, and is provided with electric power self-sufficient, green hydrogen, green alcohol and green ammonia new energy co-production and canal canal huge wheel river-through and sea-through output full-ecological enclave-sharing flight path system.

The invention relates to the technical field of equipment energy-saving management, and discloses a multi-machine linkage equipment integrated energy-saving management and intelligent decision-making method and system, and the method comprises the steps: 1, obtaining equipment operation parameters, calculating unit energy consumption, determining an operable load interval, and splitting a task into standard task units; step 2, determining group-level residual available energy consumption and establishing output and energy consumption constraints; step 3, according to the unit energy consumption and in combination with the equipment energy consumption coefficient, performing iteration to obtain a final throughput target of each equipment; step 4, calculating marginal energy consumption cost and allocating standard task units to obtain a final task allocation amount; 5, generating a strategy parameter set based on the final task distribution amount and the throughput target, monitoring an out-of-limit state, updating the strategy when the out-of-limit state is reached, and giving an alarm; and step 6, generating energy consumption settlement and management output based on the actual energy consumption and the energy consumption budget. According to the invention, intelligent management of controllable energy consumption budget, accounting of resource allocation and evaluation of energy-saving performance in a multi-machine cooperation scene is realized.

The present invention discloses a method for constructing an electrolytic hydrogen production system model, which includes the following sub-models: a. electrochemical model of an electrolyzer; b. power model of an electrolyzer; c. hydrogen production rate model of an electrolyzer; d. efficiency model of an electrolyzer; e. thermodynamic model of an electrolyzer; f. specific energy consumption model of an electrolyzer; g. compressor model; and h. hydrogen storage model. There is an influence relationship between the eight sub-models of the electrolyzer system. The electrolytic hydrogen production system model of the present application is scalable when applied to electrolyzers of different powers. The present invention achieves the establishment of a relatively simple and scalable electrolyzer system model while ensuring the accuracy of the model.

This invention relates to the field of artificial intelligence technology, specifically providing a method, system, device, and medium for energy consumption grading monitoring that combines flow direction prediction. The method includes: collecting and standardizing multi-source data from an energy system to form a standardized dataset containing flow direction data and grade data. Next, basic features and correlation features between flow direction and grade are mined from the dataset to form a feature set. This feature set is then input into a trained dual-objective prediction model, simultaneously outputting predicted energy flow rates and energy consumption grade predictions for future periods. Finally, based on the prediction results, when the probability of a target area reaching a specific energy consumption grade in the future exceeds a preset threshold, the monitoring strategy is automatically and dynamically adjusted. This invention achieves intelligent linkage between prediction and monitoring, effectively improving the timeliness of early warning and the accuracy of response.

A system for synthesizing biodiesel from a mixed oil feedstock consisting of equal parts of waste grease and Pongamia oil, the system comprising: (a) a pretreatment and mixing unit configured to filter the crude oils and mix them uniformly at elevated temperature and controlled agitation speed to form a homogenized blended oil; (b) a titration and analysis unit designed to determine the free fatty acid (FFA) content of individual and mixed oils to assess suitability for direct interesterification; (c) a transesterification unit comprising a reactor with controlled parameters, including the alcohol to oil molar ratio, catalyst concentration, reaction temperature and reaction time, to convert the blended oil into biodiesel by base-catalyzed transesterification; (d) a biodiesel purification unit configured to wash and dry the raw biodiesel to remove impurities, catalyst residues and glycerin and to obtain ASTM D6751-compliant biodiesel; (e) an optimization module using an Entropy-VIKOR multi-criteria decision technique to determine optimal transesterification parameters based on biodiesel yield and fuel properties; and (f) a performance evaluation unit comprising a diesel engine test bench, emission and combustion analyzers and a data acquisition system for evaluating the produced biodiesel blends in terms of thermal efficiency, specific energy consumption, emissions and cylinder pressure characteristics.

The present invention discloses a method for estimating the remaining range of an electric vehicle, comprising: 1. acquiring vehicle parameters and vehicle-surrounding environment data of a new energy vehicle; 2. performing route planning based on a destination input by the driver, and selecting a preferred route; 3. detecting traffic data along the preferred route obtained from the route planning; 4. importing the obtained data into a comprehensive calculation module, and obtaining predicted specific energy consumption data through calculation; 5. obtaining the remaining range based on the remaining battery charge; and 6. determining whether the destination can be successfully reached based on the obtained energy consumption data and the remaining range. This invention can improve the accuracy of the remaining range estimation during the route planning process for a new energy vehicle to a target location on an actual road.

The invention discloses an intelligent building energy-saving scheme automatic generation system based on building big data, and relates to the technical field of building big data. According to the method, two reasoning models are constructed, and a first reasoning model is constructed based on environment data; a second reasoning model is constructed based on personnel distribution and time data, and the system can dynamically adjust energy efficiency prediction according to actual data quality and integrity through common complementarity energy consumption prediction of the first and second reasoning models and comprehensive selection and use of different reasoning models, so that the prediction accuracy is improved. Through comparison with historical data, abnormal energy consumption is found and corrected in time, and a specific energy consumption control signal is generated according to an energy-saving scheme adjustment matrix. And the control execution module further performs accurate control on various energy consumption equipment, such as air conditioners, illumination and ventilation equipment, according to the signals, optimizes the energy use of the building, and realizes intelligent energy-saving management.

A method of predicting energy consumption, performed by a computing device, includes: obtaining historical manufacturing data, wherein each piece of historical manufacturing data includes total energy consumption and historical performance values corresponding to manufacturing conditions, respectively, each of manufacturing conditions includes at least one of an equipment type and a product type, and each of historical performance value indicates at least one of an equipment operation duration and a product quantity; training and generating unit energy consumption prediction model using the historical manufacturing data; obtaining at least one piece of unit energy consumption of at least one manufacturing conditions using default performance values corresponding to manufacturing conditions and unit energy consumption prediction model; and outputting at least one piece of unit energy consumption. The present disclosure further provides a system of predicting energy consumption and recommending method of installing energy consumption measuring device.

The invention discloses a fully mechanized coal mining face coal rock identification method and device, and the method comprises the steps: extracting the current coal cutting number based on the coal cutting rule of a coal cutter; according to roller cutting information collected in real time, the cutting specific energy consumption of the roller passing through each support under the current coal cutter number is calculated, and a cutting specific energy consumption sequence of the current coal cutter number is formed; and obtaining a coal rock identification result according to a comparison result between the cutting specific energy consumption of the roller passing through each bracket in the cutting specific energy consumption sequence and preset coal cutting specific energy consumption. According to the embodiment of the invention, videos do not need to be collected, and the phenomenon of poor coal rock recognition effect caused by incapability of guaranteeing video clearness due to the reasons of relatively large coal dust on the working face, mist spray and the like can be avoided.

The invention discloses a performance test and evaluation method for a wet dust collector, which comprises the following steps of: selecting dust collection efficiency eta, specific energy consumption phi and dust wettability xi as evaluation parameters, and defining comprehensive quality factors of the wet dust collector; the comprehensive quality factor of the wet dust collector is calculated by comprehensively considering the mutual relation among the dust collection efficiency eta, the specific energy consumption phi and the dust wettability xi and is used for evaluating the comprehensive performance of the wet dust collector; then different wet dust collectors are selected for performance testing under the same environment condition and the same wet dust collector is selected for performance testing under different environment conditions, so that not only can the performance sequence of the different wet dust collectors under the same condition be obtained, but also the performance sequence of the same wet dust collector under the different environment conditions can be obtained; and the corresponding wet dust collector can be conveniently selected under the subsequent specific environment condition, and the wet dust collector can be specifically optimized according to the evaluation result.

The invention relates to the technical field of reinforcement learning, and particularly discloses a refrigeration dryer energy-saving control method and system based on reinforcement learning, and the method comprises the following steps: S1, obtaining the temperature and volume of to-be-treated air, pressurizing the to-be-treated air, and constructing an equation corresponding to the change of the pressure intensity of the to-be-treated air along with the volume; s2, the temperature and volume of to-be-treated air in the pressurization process are obtained, compression power consumption is calculated based on the volume sum equation, and the temperature difference and cooling power consumption are calculated; s3, a coordinate system is established with the moment in the pressurization process as the x axis and the total energy consumption as the y axis, a plurality of energy efficiency points are constructed, a fitting curve is generated, a fitting equation is obtained, and the target moment is marked; and S4, pressurizing to a target moment at rated power, obtaining the volume and temperature at the moment, measuring a standard dew point temperature and cooling. Adjustment is carried out according to the target volume and the target pressure intensity, the unit energy consumption ratio is increased, and energy efficiency loss and equipment abrasion are reduced.

The invention discloses an AI-optimized charging pile charging curve dynamic adjustment energy efficiency improvement system, and relates to the fields of artificial intelligence, intelligent charging, energy management and new energy automobiles. Aiming at the problems that a fixed charging curve of a traditional charging pile is difficult to adapt to dynamic factors, the energy efficiency is low and the service life of a battery is influenced, the system collects multi-source data such as a vehicle battery state, environmental parameters and power grid loads in real time, dynamically optimizes the charging curve through an AI algorithm, accurately adjusts output parameters of the charging pile, and is matched with energy efficiency analysis feedback and user interaction functions. Experiments show that the average charging energy efficiency is improved by 12%, the unit energy consumption is reduced by 11%, the charging time is shortened by 8%, and the health degree of the battery is improved. The system has been popularized and applied in charging operation enterprises, smart parks and the like, the charging efficiency is improved, the battery life is prolonged, and the user experience is optimized.

The present application relates to cable production and automation control technical field, concretely is a kind of control system of energy-saving cable extrusion production process, comprising: data acquisition module, obtains the real-time working condition parameter of extrusion production line;Rheological thermal coupling analysis module, solve the shear heat contribution rate under current working condition;Thermal-mechanical response decoupling module, determine the thermal-mechanical response lag time difference between mechanical shear heat and cylinder heat conduction;Energy efficiency optimization calculation module, configured to generate dynamic thermal balance control strategy for non-steady state condition according to the thermal-mechanical response lag time difference and the preset unit output specific energy consumption target;Adaptive execution module, configured to output the coordinated control instruction of heating and cooling system and screw drive system based on the dynamic thermal balance control strategy, to realize the minimization of system energy consumption;The present application solves the energy confrontation phenomenon of common heating and cooling alternate operation in traditional control, greatly reduces the energy consumption of transition process.

The vacuum degassing die-casting process method comprises the following steps that S1, smelting and degassing are conducted, specifically, an aluminum alloy raw material is smelted and subjected to heat preservation for 30 minutes, inert gas is introduced through a rotary degassing machine in a gradient variable-speed mode, the gas flow is 15-20 L / min, and the operation lasts for 8-12 minutes; s2, mold pretreatment is conducted, specifically, a water-based release agent is sprayed, the temperature of the mold is controlled to 200-250 DEG C through multi-section pulse type heating, and a double-channel vacuum valve is arranged in a mold sealing groove; s3, vacuum die casting: starting a vacuum system after die assembly, enabling the vacuum degree of a die cavity to be less than or equal to 50mbar and maintaining for 3 seconds, and adopting three-stage injection control; and S4, post-treatment is conducted, specifically, after pressure maintaining is conducted for 8-12 seconds, mold opening is conducted, and graded water-cooling quenching is conducted on the casting immediately. The design of gradient variable-speed degassing and the double-channel vacuum valve is adopted, the hydrogen content of a casting is remarkably reduced, and the requirement for the long fatigue life of an automobile structural part is met; the multi-section pulse heating greatly improves the heating speed, obviously reduces the unit energy consumption, reduces the thermal fatigue of the mold, and prolongs the service life.

The invention provides a building energy management method and system, a storage medium and electronic equipment. The method comprises the following steps: determining a first model according to historical environment data and historical new energy power generation data; performing unit division on the target building, constructing a unit digital model, and determining a second model according to historical energy consumption data, historical environment data, historical equipment operation data and corresponding time node data; determining a theoretical new energy power generation data set and a theoretical unit energy consumption data set in a preset time period according to the weather prediction information, the current regional environment data, the first model and the second model, and obtaining theoretical equipment operation data in the preset time period; and according to the data and the energy storage condition and the energy storage capacity of the current energy storage equipment, an electric quantity supply strategy corresponding to the unit digital-analog in a preset time period is determined through a first preset rule. According to the invention, the problem of energy waste caused by difficulty in performing accurate energy management on the building according to the specific energy consumption condition of the building in the existing energy management method is solved.

The application discloses a building big data-based intelligent building energy-saving scheme automatic generation system and relates to the technical field of building big data; two reasoning models are constructed, a first reasoning model is constructed based on environmental data, and a second reasoning model is constructed based on personnel distribution and time data; the first and second reasoning models are complementary in performance consumption prediction; different reasoning models are selected and enabled comprehensively, the system can dynamically adjust energy efficiency prediction according to actual data quality and integrity, and the accuracy of prediction is improved; through comparison with historical data, abnormal energy consumption can be found and corrected in time, and specific energy consumption control signals are generated according to an energy-saving scheme adjustment matrix. A control execution module further controls various energy-using equipment, such as air conditioners, lighting and ventilation equipment, according to the signals, energy use of the building is optimized, and intelligent energy-saving management is realized.