75 results about "Chaos optimization" patented technology

The invention relates to a multi-target reactive power optimization method, in particular to a multi-target reactive power optimization method based on an adaptive chaos particle swarm algorithm. The method aims at solving the problem that multi-target reactive power optimization control variables are probably trapped in a locally optimal solution, and the speed for acquiring an optimal solution is low. The method includes the steps that firstly, original data of a particle swarm are input to an adaptive chaos particle swarm optimization algorithm program; secondly, first m particles are selected from the particle swarm as initial positions of the particle swarm according to fitness values in a preferred mode; thirdly, inertia weights w of the particles are acquired through calculation of inertia weight coefficients, and first M preferred particles are selected from the particle swarm for chaos optimization calculation; fourthly, the speed and the positions of the particles are updated according to the particle swarm reactive power optimization algorithm, and then iteration allowances and values of the control variables can be acquired; fifthly, whether iteration stop conditions are met or not is judged, and then the multi-target reactive power optimization method based on the adaptive chaos particle swarm optimization algorithm is finished. The multi-target reactive power optimization method is applied to the field of electric systems.

The invention discloses a system for detecting a sea target by a chaos optimizing radar, comprising a radar, a database and an upper computer, wherein the radar, the database and the upper computer are successively connected; the radar irradiates a detected sea area; radar sea clutter data are stored in the database; the upper computer comprises a data preprocessing module, a modeling module of a forecast model, a chaos optimization module, a sea clutter forecast model, a discriminative model updating module and a result displaying module. The invention also provides a method for detecting a sea target by a chaos optimizing radar. The invention provides the system and the method for detecting a sea target by a chaos optimizing radar, which have high precision and avoid the influence of the manual factor.

The invention relates to a three-dimensional unstable state monitoring and abnormity diagnosis and maintenance system of a blast furnace hearth, belonging to the technical field of online monitoring, diagnosis, prewarning and maintenance of the blast furnace. The three-dimensional unstable state monitoring and abnormity diagnosis and maintenance system of the blast furnace hearth comprises a data acquisition module, a data filtering module, a hearth and furnace bottom corrosion and accretion calculation module, an abnormality diagnosis module, a prewarning displaying module and a hearth-guiding and maintaining module. Water temperature of a cooling wall of the hearth and galvanic couple temperature of a furnace body can be collected and filtered in real time; by combining the two data together and using pro and con questions of the heat transmission science in combination with the standard of abnormity diagnosis, the influence of the abnormity possibly occurring in the production of the thermal conductivity coefficient variation of refractories, the ring shake, the air gap, and the like on distribution and corrosion of a temperature field is comprehensively judged, a gradient-regularization method and a chaos optimization method are combined to solve, the online monitoring on the three-dimensional unstable state temperature field of the hearth and the furnace bottom, the internal corrosion type, the slag-metal skull variation and the hot state of the hearth is realized, the abnormal circumstance and the corrosion deterioration causes are diagnosed in real time, and the hearth maintenance means is pertinently guided according to the corrosion deterioration causes. The system is successfully applied to industry.

The invention discloses an improved chaos ant colony algorithm-based unmanned aerial vehicle airway planning method. The method comprises the following steps: 1, converting an optimized solution obtained by a chaos optimization algorithm into a pheromone initial value of an ant colony algorithm; and 2, performing airway optimization through the ant colony algorithm, and performing chaotic mappingon the eligible airway after the optimization ends to obtain an optimal airway. The pheromone initial value of every ant difference, generated by using chaotic mapping substitutes the same pheromone initial value of original ants in order to generate an ant colony algorithm-based new initial airway, so the searching efficiency of the algorithm is improved; and a chaotic disturbance pheromone update strategy is introduced to dynamically update the pheromone with the obtained effective airway, so local optimal defects are effectively overcome, and the convergence speed is improved.

The invention relates to a roundness error evaluation method based on a variable-metric chaotic simulated annealing algorithm. The roundness error evaluation method comprises the following steps of: taking the simulated annealing algorithm as optimizing coarse searching first, and then taking the high efficiency of a chaos optimization algorithm as optimizing fine searching to ensure that the optimizing process is concise and efficient. Because the optimizing result of the simulated annealing algorithm is independent of an initial value, an actual globally optimal area is searched by adopting the simulated annealing algorithm, and the chaos optimization algorithm is excellent in execution efficiency and is suitable for carrying out fine searching in the globally optimal area, thereby searching a globally optimal solution, and therefore fewer iterations are obtained in the optimization process; and meanwhile, the chaotic mapping xtin=cos (1 / xtin2) provided by the invention can better realize chaotic optimizing, the [a1, i+1, b1, i+1] and [a2, i+1, b2, i+1] are ceaselessly decreased according to the solution space variation in the execution process, and therefore the optimizing process ceaselessly approaches to the globally optimal solution.

The invention relates to the technical field of power distribution networks, in particular to a method for planning a power distribution network comprising photovoltaic power supply. The method comprises the following steps: (1) establishing a target function of social cost; (2) determining a constraint condition; and (3) determining the planning method with a particle swarm algorithm containing chaos optimization, outputting the optimal planning scheme and determining the optimal access position and capacity of the photovoltaic power supply. According to the method, the optimal access position and capacity of the photovoltaic power supply are calculated, so that the network loss of the power distribution network is reduced; the operating cost of the power distribution network is reduced; the voltage of a system is improved; the load capacity of the system is enhanced; safe and effective operation of the power distribution network can be ensured; and the economic benefits can also be further improved.

The invention belongs to the field of the analysis of nonlinear time series, in particular to a time series predicting model. The network model comprises an input layer, a middle layer and an output layer, wherein the middle layer unit consists of a chaos operator with the chaos characteristic. The parameter of the chaos operator is trained and adjusted through a chaos optimization algorithm. By learning and training, the network predicts the value at a certain time in future with the previous known value of the time series, and gradually modifies the parameter of the chaos operator according a predicted error, thereby gradually having the information which is accordant with the regularity in the time series and completing the predicting function of the time series. Particularly, the model can effectively realize the multi-step prediction of the time series. The time series is mainly used for the field of the prediction and the analysis of the time series in the practical engineering.

The invention provides an energy-saving control system with chaos optimization-based SVM prediction for sewage treatment. The system comprises a computer network system used for realizing the integration of management and control, an activated sludge and sewage treatment system model module, a production process control module and a production management scheduler module, wherein the production management scheduler module, the production process control module and the activated sludge and sewage treatment system model module are sequentially connected by the computer network system. When being used for the running of a sewage treatment plant, the system not only can reduce the energy consumption of the sewage treatment plant by 15 to 25 percents, but also can upgrade the treatment effect of the sewage treatment plant by one degree on the basis of the original design, thereby having huge potential.

The invention relates to a microgrid economic optimal operation design method with a demand response included. The method comprises the following steps: 1) a microgrid optimal design database is built; 2) an optimization model is built, wherein the objective function for the optimization model is the minimum total cost of the microgrid operation, and constraint conditions comprise a power balance constraint, a controllable unit output constraint, a controllable unit ramp constraint, a tie line transmission power constraint and a controllable load capacity constraint; 3) the input variable parameter value needed by the optimization model is acquired from the microgrid optimal design database, an improved genetic algorithm based on chaos optimization is adopted to solve the optimization model, and output data of a decision variable of the optimization model are acquired; and 4) the total microgrid operation costs under all scenes are compared according to the output data of the decision variable, and the optimal scene and the corresponding interruptible load optimal control strategy can be acquired. Compared with the prior art, the method of the invention realizes more reasonable, more economic and more efficient mircrogrid energy utilization from aspects of a demand side and management operation.

The invention provides a least square support vector machine (LSSVM) periodic weighting prediction method based on wavelet and chaos optimization. The method utilizes the wavelet decomposition technology to enable selected sample set data to be decomposed into components of different frequencies. A component phase space is reconstructed on the basis of the chaos theory, the reconstructed components are trained by using LSSVM models, parameters of LSSVM prediction models are optimized through chaos particle swarm optimization, and finally wavelet reconstruction is performed on prediction components obtained by the LSSVM models to whole periodic weighting load prediction waveforms. Through wavelet decomposition of a periodic load, reconstruction of a load phase space on the basis of the chaos theory, construction of a least square support vector machine, and chaos particle swarm optimization of the parameters, the LSSVM periodic weighting prediction method based on the wavelet and the chaos optimization can predict periodic weighting load waves at some period of reconstructed waves when load time sequence has certain chaos characteristics and can be widely used for prediction of periodic weighting load to be born of a support.

The invention discloses a chaos optimization method for on-line coal quality parameter calculation, which includes the following steps: the real-time parameters of a thermal power unit, such as the coal feed quantity of a coal feeder, the primary wind flow and primary wind temperature of the inlet of a coal pulverizer, the wind-powder mixture temperature of the outlet of the coal pulverizer and the power of the coal pulverizer, are acquired; the parameters of intermediate unknown variables, such as carbon dioxide gas volume, sulfur dioxide gas quantity calculated according to dry basis components and carbon dioxide gas quantity calculated according to dry basis components in exhausted flue gas, are set; a chaos optimization algorithm is adopted to jointly work out the dry ash-free basis component, dry ash-free basis hydrogen component, dry ash-free basis oxygen component, dry ash-free basis nitrogen component and dry ash-free basis sulfur component of coal, as-received basis moisture, as-received basis ash and net calorific value. The method utilizes the real-time soft measurement technology of analyzing as-fired coal elements and net calorific value by using the chaos optimization algorithm to work out the real-time information of coal quality.

The invention discloses a lithium-ion battery remaining life prediction method. The method comprises the steps that (1) chaos particles are initialized; (2) fitness assessment is performed; (3) individual optimal values and a global optimal value of the particles are updated; (4) the velocities and positions of the particles are updated according to a PSO algorithm formula; (5) the optimal position is subject to chaos optimization; (6) whether each iteration meets an ending requirement or not is judged; and (7) a CPSO-SVR model is used to perform training and prediction on a dataset. Accordingto the method, a chaos algorithm is adopted to improve a PSO algorithm, the particle appearing at the optimal position in a generated chaos sequence randomly replaces a certain particle in a currentparticle swarm, so that inert particles are urged to get rid of local optimum, jump out of constraint and are initialized again according to the chaos sequence, and an optimal solution is quickly found through search in space. An improved CPSO-SVR algorithm is adopted to predict the remaining life of a lithium-ion battery, and compared with a PSO-SVR algorithm, higher prediction precision is achieved.

The invention discloses a self-adaptation polarline correcting method based on an infrared binocular camera. Only two infrared images are needed to serve as the input, and an infrared binocular image is preprocessed to achieve the contrast enhancement; SIFT feature points are extracted from the two infrared images respectively, and matching points are obtained through matching; when the error matching is processed, and the error matching point is eliminated according to the improved outlier detection idea based on the neighbor degree; the global optimization is carried out through the improved particle swarm optimization introducing the chaos optimization idea and the hybrid idea in the genetic algorithm, and two transformation matrixes are obtained; pixel mapping is carried out on the two infrared images according to the corresponding transformation matrixes, and then the corrected binocular image can be obtained. The experiment shows that the method can be suitable for most scenes and has very high correction precision and self-adaptability.

An embodiment of the invention discloses a method and a device for classifying network traffic on the basis of grey wolf algorithms. The method for classifying the network traffic on the basis of the grey wolf algorithms in the embodiment of the invention includes S1, carrying out multilevel and multi-scale preprocessing decomposition on network traffic data by means of wavelet packet transformation; S2, optimizing FCM (fuzzy C-means) clustering algorithm models by the aid of novel swarm intelligence algorithms-grey wolf horizontal-vertical multi-dimensional chaos optimization algorithms and classifying decomposed network traffic data by the aid of the FCM clustering algorithm models. The method and the device have the advantage that the technical problems of low decomposition accuracy and influence on network traffic clustering and classification in late periods due to the fact that existing network traffic is only decomposed on low-frequency portions by means of wavelet transformation when multi-scale decomposition is carried out on the existing network traffic by the aid of existing methods for classifying the existing network traffic can be solved by the aid of the method and the device, and the technical problems of low network traffic classification and identification accuracy and efficiency of models due to the fact that the clustering optimization models on the basis of swarm intelligence algorithms are easy to fall into local optimal solution and are low in convergence speed also can be solved by the aid of the method and the device.

The invention discloses a network switching side control method for a terminal group access network based on cognitive radio, comprising the following steps that: each user terminal (CEP(Central Processing Element)) broadcasts own bandwidth request messages to accessible base stations (BS) through a public control channel according to own spectrum sensing result, traffic demand, own signal-to-noise ratio and access probability of a plurality of base stations; after receiving the request messages, the base stations transmit the messages to a network switching manager at a core network side; the core network quickly solves a cognitive terminal group network distribution scheme, in which load on each base station is balanced, through a chaos optimization algorithm according to the messages, and transmits the result to the base stations to which the CPEs access; and the base stations finish the network switching for the user terminal group by sending an access response message to corresponding CPEs. With the method, frequent network switching in the radio network of the prior art is reduced, and a plurality of CPEs, which need to be switched between networks simultaneously, can access to the network meeting own communication demands, more fairly.

The invention discloses a photovoltaic array maximum power point tracking method based on chaos optimization search. By sampling the direct-current voltage Vpv and the current Ipv which are output by a photovoltaic array in real time, the output power p(k) of the photovoltaic array is calculated and compared with the current maximum power value p* prestored by an MPPT controller; if p(k)>p*, the value of p(k) is assigned to p*, and the value of Vpv is assigned to the output voltage x* of the MPPT controller; otherwise, the value of p(k) is abandoned, and the value of p* and the value of x* are kept unchanged. Then, the voltage x* output by the MPPT controller and the voltage Vpv output by the photovoltaic array are added to a summator, and a generated error voltage is added to the in-phase end of the summator after being subjected to the proportion-integration link and then compared with a sawtooth voltage added to the anti-phase end of a comparator, so that the duty ratio of gate drive signals of a switch tube in a DC / DC converter is changed, the parameters of a DC / DC conversion circuit are regulated and controlled, and maximum power tracking control can be achieved. The photovoltaic array maximum power point tracking method based on chaos optimization search is high in tracking speed and control precision.

The invention proposes a chaos grey wolf optimization-based unmanned aerial vehicle formation control method. A distributed model predictive control (MPC) frame of unmanned aerial vehicle formation control is built, each unmanned aerial vehicle only shares information with a neighbor, and the communication requirement and the computational complexity are reduced; a chaos optimization algorithm iscombined with a grey wolf optimization algorithm, and thus, the algorithm performance is improved; and the algorithm is combined with the distributed MPC, finite horizon optimal control problem (FHOCP) is solved, so that unmanned aerial vehicle formation control is achieved.

The invention discloses a wavelet weighted multi-mode blind equalization method based on the chaos optimization of a support vector machine. The method comprises the following steps of: operating a complex signal source transmission signal by using a pulse response channel, and thus obtaining a channel output vector; summating a channel noise and the channel output vector, and thus obtaining an input signal of an orthogonal wavelet transformer; performing orthogonal wavelet transformation on the input signal of an equalizer, and thus obtaining the input signal of the equalizer; operating the input signal of the equalizer by using the equalizer, and thus obtaining an output signal of the equalizer; and operating the output signal of the equalizer by using a judger, and updating the weight vector of the equalizer by using a weighted multi-mode blind equalization method. The method has the advantages that: by using the support vector machine, the weight vector of the wavelet weighted multi-mode blind equalization method is initialized; a convergence speed can be improved, and the immergence of a local minimal value point is avoided; parameters of the support vector machine are selected for parameter combined optimization; combined optimization target functions are established; the optimum target function value is searched by chaos optimization; and the fitting capacity of the support vector machine is improved.

The invention discloses a wastewater treatment process soft-sensing modeling method based on a chaos-fireworks hybrid algorithm. For improving quality of initial fireworks members of an FWA (Fireworksalgorithm), improved two-level sine chaos mapping is defined in the method. For improving optimization performance of the basic FWA and fusing a chaos optimization algorithm and the FWA, the chaos-fireworks hybrid optimization algorithm is provided. According to the method, information exchange and sharing among members in populations are effectively enhanced, diversity of the populations is improved, search ranges in solution space are enlarged, and premature convergence of the algorithm is avoided. In addition, a new sample similarity measurement index is defined for the soft-sensing modeling problem of dissolved-oxygen (DO) mass concentration of a wastewater biochemical-treatment process, and a representative-sample extraction method is provided, and is used for extracting more representative modeling data. The improved chaos-fireworks hybrid optimization algorithm is applied to neural-network training in soft-sensing modeling, and good application effects are obtained.

The invention discloses a visible light positioning method resistant to NLOS interference. A traditional TDOA based VLC positioning algorithm needs an accurate time detector, has high requirements forhardware equipment and is high in cost. In the aspect of reception algorithms, a positioning algorithm resistant to NLOS interference is used, a chaotic optimization algorithm is used to estimate aninitial position, a Taylor series expansion algorithm is combined to carry out recursive operation of a reception-end position, and a final accurate positioning point is obtained. Compared with a traditional reception-end positioning algorithm, the chaotic algorithm is more accurate in positioning and has lower errors. Under the condition of the same facilities, illumination requirements are met,a higher positioning service with higher precision than the traditional method can be provided, and the application prospects are wider.

The invention relates to an adjustment and parameter optimization method of a molecule reaction dynamic model (namely the Kumar molecule reaction dynamic model) for preparing ethylene molecules through naphtha high-temperature steam cracking and belongs to the field of ethylene cracking furnace process simulation and production operation optimization engineering. Reaction kinetic parameters are adjusted in a self-adaptive mode through the chaos optimization method according to characteristics and constitutions of different kinds of naphtha, furnace profile structures and operation conditions with carbon-hydrogen balance, the minimum product yield error and fine adjustment of secondary reaction kinetic parameters considered, the reaction model better adapts to different kinds of naphtha, and accuracy of process models is improved. The invention further provides a software system for achieving the method. Primary selectivity coefficients and secondary reaction kinetic parameters of the Kumar model can be automatically adjusted according to characteristics of different kinds of naphtha, the defect that an original model is poor in naphtha adaptability is overcome, and the naphtha high-temperature steam cracking process and product distribution can be accurately simulated according to different furnace profile structures and operation conditions.

The invention discloses a configuration method of a UPFC in a wind power collection area. The method comprises the steps of establishing an objective function, determining the variation of a load rate, voltage and transmission losses before and after mounting of the UPFC, performing constant volume calculation according to a preset algorithm to obtain a candidate solution of a preset function, exploiting a first optimal solution near the candidate solution according to a kent chaos search strategy, performing chaos optimization processing on the first optimal solution to exploit a second optimal solution, determining global optimal point information according to an obtained nth optimal solution after iteration processing for n times, and then configuring site selection of the UPFC according to the global optimal point information. The method solves the problems of transmission capacity reduction and heavy line load in the wind power collection area, and improves an optimization configuration effect of the UPFC.

The invention discloses a comprehensive evaluation method for slope stability and safety level. The method comprises the following steps: (1) collecting sample indexes influencing slope stability; (2)normalizing the collected sample indexes; (3) determining slope safety grade division and index grade standards; (4) establishing a stability evaluation PP model; and (5) determining a slope stability grade. Chaos optimization and particle swarm optimization are combined, the optimal projection direction of an evaluation index is optimally searched, chaos disturbance is generated for evolution-stopped particles by means of the characteristics of chaos variables in optimization, a solution jumps out of a local extremum region, and meanwhile, the search precision and the algorithm efficiency are improved by using self-adaptive adjustment inertia weight. A projection value interval range corresponding to each grade of the slope is solved by utilizing the solved optimal projection direction and the normalized interval upper and lower limit values of the indexes corresponding to each grade, and the stability grade of the to-be-evaluated slope is determined by comparing and searching the slope grade corresponding to the interval where the projection value of the to-be-evaluated slope is located.

A system for radar sea clutter forecast by using chaos optimization comprises a radar, a database and a host computer, wherein the radar, the database and the host computer are orderly connected; the radar irradiates on to-be-detected sea area, and saves radar sea clutter data into the database; the host computer comprises a data preprocessing module, a forecast model modeling module, a chaos optimizing module, a sea clutter forecasting module, a discrimination model updating module and a result display module. Besides, the invention also provides a chaos optimizing radar sea clutter forecasting method. In a word, the invention provides a high-precision system and method for radar sea clutter forecast by using chaos optimization, which can rapidly search optimization and avoid influence of human factor.

The invention relates to a PSS (power system stabilizer) parameter dynamic coordination method and device based on chaotic optimization. The device comprises the following steps of: (1) reading data in an energy management system; (2) dividing a PSS in each generator of the system into n layers according to weight; (3) constructing a multi-object layered optimization equation; (4) establishing a mapping relation between a chaos variable quantity Tk and an optimization variable xk; (5) carrying out iterative search on the xk, solving the layered optimization equation so as to obtain the optimal value of the Fk(xk) and the xk corresponding the optimal value; (6) constructing a sub objective function equation in each layer, and solving Yk and the optimal value of the Fk(yk); and (7) firstly judging the type of the PSS in the optimal object equation according to a condition. The method provided by the invention has the beneficial effects that the method can effectively and dynamically adjust a PSS parameter of each generator, so as to restrain the low frequency oscillation of the system and improve the stability in operation of a power grid; and the division of a device module based on the method is distinct, the structure is simple, and the method is easy to implement.

The invention discloses a visible light positioning method and system with double-carrier chaos optimization, and relates to the field of visible light positioning. The method includes: determining the positions of LED lamps according to ID information received by a receiving end, of the LED lamps, obtaining the distance between the receiving end and each LED lamp according to an attenuation factor of the light intensity, and determining a three-dimensional coordinate of a positioning point by employing a chaos optimization algorithm; and introducing a dynamic adjusting factor in a secondary carrier process, generating random disturbance by employing a chaos variable, reducing the amplitude of random disturbance with search, and determining the accurate position of the positioning point. According to the method, the positioning process is simple, the calculation amount in the positioning process is reduced through the secondary carrier process, and the positioning accuracy is improved.

The invention discloses a photovoltaic array maximum power point tracking method based on chaos optimization search. By sampling the direct-current voltage Vpv and the current Ipv which are output by a photovoltaic array in real time, the output power p(k) of the photovoltaic array is calculated and compared with the current maximum power value p* prestored by an MPPT controller; if p(k)>p*, the value of p(k) is assigned to p*, and the value of Vpv is assigned to the output voltage x* of the MPPT controller; otherwise, the value of p(k) is abandoned, and the value of p* and the value of x* are kept unchanged. Then, the voltage x* output by the MPPT controller and the voltage Vpv output by the photovoltaic array are added to a summator, and a generated error voltage is added to the in-phase end of the summator after being subjected to the proportion-integration link and then compared with a sawtooth voltage added to the anti-phase end of a comparator, so that the duty ratio of gate drive signals of a switch tube in a DC / DC converter is changed, the parameters of a DC / DC conversion circuit are regulated and controlled, and maximum power tracking control can be achieved. The photovoltaic array maximum power point tracking method based on chaos optimization search is high in tracking speed and control precision.

The invention discloses a discrete sliding mode trajectory and speed tracking control method for a high-speed train. The method comprises the following steps: constructing a nonlinear train model of the train, and assigning estimation parameters; with displacement and control input quantities as the input and output data for model optimization, and discretizing and linearizing the nonlinear trainmodel so as to obtain a discrete linear train model with optimized model parameters; designing an extended Kalman filter oriented to the discrete and linearized model to obtain filtered train displacement and an estimated speed; designing a high-speed train trajectory tracking controller by adopting a discrete sliding mode method, and designing an interference observer to estimate model uncertainty and linearized errors so as to improve train tracking precision. According to the invention, train model parameters are estimated by adopting a chaos optimization method, the nonlinear train model is discretized and linearized, and then train displacement and speed estimation is designed by adopting a discrete extended Kalman filtering method, so measurement noise interference of train displacement is relieved, and the problem of speed sensor faults is solved.

The invention discloses a time sequence prediction method based on a chaotic optimization neural network model, and the method comprises the steps: firstly obtaining urban historical daily water demand time sequence data online from a database, carrying out the data preprocessing, and carrying out the chaotic feature recognition; determining the structure of the chaos optimization BP neural network by using the embedded dimension of the model input data reconstruction phase space, and carrying out model training at the same time; finding a global optimal value of the BP neural network weight through chaotic optimization search in the model training process; after model training is finished, carrying out chaotic parameter control on an output time sequence predicted value through a parameter control method; and finally, realizing prediction of the urban daily water demand time sequence. The urban daily water demand time series prediction method based on the chaotic optimization neural network model needs few training data samples, is high in convergence rate, can easily reach a global minimum value, is good in prediction result overall error index, and shows good comprehensive prediction performance.

The invention relates to a CCHP microgrid operation optimization method. The method comprises the steps of S1, constructing a microgrid system model; s2, constructing a microgrid operation data set; s3, establishing a target function of the microgrid economic operation optimization model; s4, establishing constraint conditions of the microgrid economic operation optimization model; and S5, solvingan optimal solution of the economic optimization problem of the CCHP microgrid based on a Q learning and quantum particle swarm optimization algorithm. According to the method, population initialization is optimized by utilizing a chaos optimization algorithm, so that the diversity of particles can be increased, the global optimum searching capability is improved, and the probability of falling into global optimum is low. Meanwhile, the search capability of each particle for the optimal solution is further improved by adopting a crisscross algorithm, a better optimization effect can be obtained when economic optimization is carried out on the cold-heat-electricity combined supply microgrid, the problem that the economic optimization problem is likely to fall into local optimization is effectively solved, and a better economic optimization result is obtained.