A smart plant energy dispatching system and method based on digital twin technology

Abstract

The present invention discloses an intelligent factory energy dispatching system and method based on digital twin technology, the system comprising: a factory energy dispatching system physical space module, a factory energy dispatching system digital space module, a twin data service platform module, and a cloud platform module; the present invention combines the digital twin system to digitally and accurately simulate the physical industrial factory workshop and production line to achieve precise regulation; the system energy supply strategy is optimized through the optimized fish algorithm to achieve the optimal system supply strategy, thereby effectively reducing the carbon emissions of the factory workshop.

Description

Technical Field

[0001] The present invention relates to the field of cloud computing technology, and in particular to an intelligent plant energy scheduling system and method based on digital twin technology. Background Art

[0002] Traditional factories use electricity generated by traditional energy, and their operating costs are extremely high. Regardless of whether it is needed or not, the factory workshops must basically maintain 24-hour power supply every day, and they cannot perform intelligent energy regulation based on the power consumption of the factory workshops. Due to the relatively single energy supply and low utilization rate of clean energy, the factory's carbon emissions will be relatively high.

[0003] At this stage, there is an urgent need for an intelligent factory energy dispatching system to regulate the optimal operating mode of the factory energy supply, improve the factory energy utilization rate, reduce primary energy consumption, reduce carbon emissions, and reduce the economic cost of factory operation. Summary of the invention

[0004] Purpose of the invention: The purpose of the present invention is to provide an intelligent factory energy scheduling system and method based on digital twin technology to solve the problem of excessive energy consumption and carbon emissions in factory workshops at this stage.

[0005] Technical solution: The intelligent plant energy dispatching system based on digital twin technology described in the present invention includes: a physical space module of the plant energy dispatching system, a digital space module of the plant energy dispatching system, a twin data service platform module, and a cloud platform module; the physical space module of the plant energy dispatching system is used to transmit physical data to the twin data service platform module and receive simulation data from the digital space module of the plant energy dispatching system; the digital space module of the plant energy dispatching system is used to receive data sent by the physical space module of the plant energy dispatching system through a wireless network and perform data mapping; the twin data service platform module is mainly used to collect data information of the physical space module of the plant energy dispatching system and the digital space module of the plant energy dispatching system, and send the corresponding data processing results to the cloud platform, the physical space module of the plant energy dispatching system and the digital space module of the plant energy dispatching system; the cloud platform module is used to collect the data of the physical space module of the plant energy dispatching system, the digital space module of the plant energy dispatching system and the twin data service platform as a whole and process and calculate a large amount of data.

[0006] Furthermore, the connection relationship between the modules is set as follows: the physical space module of the plant energy dispatching system is connected to the digital space module of the plant energy dispatching system; the twin data service platform module is respectively connected to the digital space module of the plant energy dispatching system and the physical space module of the plant energy dispatching system; the twin data service platform module is connected to the cloud platform module.

[0007] The invention discloses a smart plant energy dispatching method based on digital twin technology, using the improved The fish optimization algorithm calculates the optimal energy supply strategy for the plant, including the following steps:

[0008] (1) Establish the objective function;

[0009] (2) Initialization The position of the fish population, the maximum number of iterations and the population size are used to calculate the adaptive inertia weight;

[0010] (3) Based on the elite strategy of the sailfish optimization algorithm, the sailfish optimization algorithm formula is improved to calculate the randomly generated energy supply strategy;

[0011] (4) Calculate the local optimal solution;

[0012] (5) Use the whale algorithm to update the local optimal solution;

[0013] (6) Calculate the global optimal solution, i.e., the optimal energy supply strategy for the plant.

[0014] Furthermore, the step (1) is specifically as follows:

[0015]

[0016] C=βP Grid

[0017] O=min(Q E EF grid,OM )+min(βP Grid )

[0018] in, is the CO2 emissions of electricity generated by the production system, Q E is the total annual power supply of the plant system, EF grid,OM is the grid baseline CO2 emission factor, C min is the economic cost, β is the distributed electricity price, P Grid It is the overall electricity consumption of the factory workshop.

[0019] Furthermore, the step (2) initializes The calculation formula for the fish population position is as follows:

[0020] O i =lb+rand×(ub-lb) (1)

[0021] Among them, O i is the position of individual i, that is, any system strategy generated by initialization; lb and ub are the lower and upper bounds of the search space, and rand is a random number between 0 and 1;

[0022] exist An inertia weight w that changes with the number of iterations is added to the fish position update, according to The change of the update number in the fish optimization algorithm, the adaptive inertia weight formed by the number of iterations t is as follows:

[0023]

[0024] Among them, the inertia weight w represents a property that changes nonlinearly between [0,1].

[0025] Furthermore, the step (3) is specifically as follows:

[0026]

[0027] Where t is the current iteration number, The current best Fish individuals, that is, the currently obtained local optimal supply strategy, For the current random Fish individuals, i.e. randomly generated energy supply strategies.

[0028] Furthermore, the step (4) is specifically as follows: The fish's position and the current host's position are compared. The fish moves in a small range around the host to determine whether to change the host. The calculation formula is as follows:

[0029]

[0030] Among them, O att yes A tentative move of the fish, O pre Indicates the previous generation The position of the fish, i.e., the local optimal supply strategy in the last search, randn is a normally distributed random number between 0 and 1;

[0031] After a small movement, The fish determines whether to change the host, and the calculation formula is as follows:

[0032]

[0033] If replaced, the calculation formula is as follows:

[0034] H(i)=round(rand)

[0035] Among them, H(i) determines The host of the fish parasite, the initial value is 0 or 1; if H(i) is equal to 0, it adsorbs whales, if H(i) is equal to 1, it adsorbs swordfish; round is the rounding function; and f(O att) are respectively With O att The fitness value of .

[0036] Furthermore, the step (5) is specifically as follows:

[0037]

[0038]

[0039] k=rand×(a-1)+1

[0040]

[0041] Where D represents the distance between the optimal position before the update and the current position, k is a random number between -1 and 1, a decreases linearly between [-2, 1] during the iteration, and T is the maximum number of iterations.

[0042] Furthermore, the step (6) is specifically as follows:

[0043]

[0044]

[0045] B=2×V×rand-V

[0046]

[0047] Among them, A is The distance the fish moves, which is related to Fish is related to the host size, Fish factor C is limiting The position of the fish, its value is 0.1, B is the volume of the simulated host, V is the simulated The volume of the fish, O Best That is, the optimal energy supply strategy for the plant in the iterative results.

[0048] A device described in the present invention includes a memory, a processor, and a program stored in the memory and executable on the processor, and is characterized in that when the processor executes the program, the steps in any one of the above-mentioned smart plant energy scheduling methods based on digital twin technology are implemented.

[0049] Beneficial effects: Compared with the prior art, the present invention has the following significant advantages: by combining the digital twin system, the physical industrial workshop and production line can be digitally simulated and precisely controlled; The fish algorithm optimizes the system energy supply strategy to achieve the optimal system supply strategy and effectively reduce carbon emissions in factory workshops. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a schematic diagram of the system structure of the present invention;

[0051] Figure 2 For the present invention Fish algorithm flow chart;

[0052] Figure 3 This is a comparison chart of carbon emissions of the present invention. DETAILED DESCRIPTION

[0053] The technical solution of the present invention is further described below in conjunction with the accompanying drawings.

[0054] like Figure 1 As shown, an embodiment of the present invention provides an intelligent plant energy dispatching system based on digital twin technology, including: a plant energy dispatching system physical space module, a plant energy dispatching system digital space module, a twin data service platform module, and a cloud platform module; the plant energy dispatching system physical space module is used to transmit physical data to the twin data service platform module and receive simulation data from the plant energy dispatching system digital space module; the plant energy dispatching system digital space module is used to receive data sent by the plant energy dispatching system physical space module through a wireless network and perform data mapping; the twin data service platform module is mainly used to collect data information of the plant energy dispatching system physical space module and the plant energy dispatching system digital space module, and send the corresponding data processing results to the cloud platform, the plant energy dispatching system physical space module and the plant energy dispatching system digital space module; the cloud platform module is used to collect the data of the plant energy dispatching system physical space module, the plant energy dispatching system digital space module and the twin data service platform as a whole and process and calculate a large amount of data. The connection relationship between the modules is set as follows: the physical space module of the plant energy dispatching system is connected to the digital space module of the plant energy dispatching system; the twin data service platform module is connected to the digital space module of the plant energy dispatching system and the physical space module of the plant energy dispatching system respectively; the twin data service platform module is connected to the cloud platform module.

[0055] like Figure 2 As shown, the embodiment of the present invention also provides an intelligent plant energy scheduling method based on digital twin technology, using the improved The fish optimization algorithm calculates the optimal energy supply strategy for the plant, including the following steps:

[0056] (1) Establish the objective function; specifically:

[0057]

[0058] C=βP Grid

[0059] O=min(Q E EF grid,OM )+min(βP Grid )

[0060] in, is the CO2 emissions of electricity generated by the production system, Q E is the total annual power supply of the plant system, EF grid,OM is the grid baseline CO2 emission factor, C min is the economic cost, β is the distributed electricity price, P Grid It is the overall electricity consumption of the factory workshop.

[0061] (2) Initialization Fish population position, maximum number of iterations and population size, calculate adaptive inertia weights; initialize The calculation formula for the fish population position is as follows:

[0062] O i =lb+rand×(ub-lb) (1)

[0063] Among them, O i is the position of individual i, that is, any system strategy generated by initialization; lb and ub are the lower and upper bounds of the search space, and rand is a random number between 0 and 1;

[0064] exist An inertia weight w that changes with the number of iterations is added to the fish position update, according to The change of the update number in the fish optimization algorithm, the adaptive inertia weight formed by the number of iterations t is as follows:

[0065]

[0066] Among them, the inertia weight w represents a property that changes nonlinearly between [0,1], which can fully guarantee the convergence of the algorithm.

[0067] (3) Based on the elite strategy of the sailfish optimization algorithm, the sailfish optimization algorithm formula is improved to calculate the randomly generated energy supply strategy; specifically: equivalent to adsorption following (exploration phase): SFO When the fish attaches to the swordfish, The fish will follow the sailfish. Based on the elite strategy of the SFO algorithm, the formula of the SFO algorithm is improved. The calculation formula is as follows:

[0068]

[0069] Where t is the current iteration number, The current best Fish individuals, that is, the currently obtained local optimal supply strategy, For the current random Fish individuals, i.e. randomly generated energy supply strategies.

[0070] (4) Calculate the local optimal solution; specifically: When fish attach to the host, they will The fish's position and the current host's position are compared. The fish moves in a small range around the host to determine whether the host needs to be changed. This process is similar to the accumulation of experience. The mathematical calculation formula is as follows:

[0071]

[0072] Among them, O att yes A tentative move of the fish, O pre Indicates the previous generation The position of the fish, i.e., the local optimal supply strategy in the last search, randn is a normally distributed random number between 0 and 1;

[0073] After a small move, The fish determines whether to change the host, and the calculation formula is as follows:

[0074]

[0075] If replaced, the calculation formula is as follows:

[0076] H(i)=round(rand)

[0077] Among them, H(i) determines The host of the fish parasite, the initial value is 0 or 1; if H(i) is equal to 0, it adsorbs whales, if H(i) is equal to 1, it adsorbs swordfish; round is the rounding function; and f(O att ) are respectively With O att The fitness value of .

[0078] (5) Use the whale algorithm to update the local optimal solution; specifically: equivalent to the development stage, WOA strategy; when the host is a whale, The fish will move in sync with the whale, continuing to search for the optimal strategy within the range.

[0079]

[0080]

[0081] k=rand×(a-1)+1

[0082]

[0083] Where D represents the distance between the optimal position before the update and the current position, k is a random number between -1 and 1, a decreases linearly between [-2, 1] during the iteration, and T is the maximum number of iterations.

[0084] (6) Calculate the global optimal solution, i.e., the optimal energy supply strategy for the plant. Specifically, it is equivalent to the host foraging stage; the host foraging stage is a further subdivision of the development stage, with a smaller search range. The fish will search for food around the host, no longer considering adsorption, and the calculation formula is as follows:

[0085]

[0086]

[0087] B=2×V×rand-V

[0088]

[0089] Among them, A is The distance the fish moves, which is related to Fish is related to the host size, Fish factor C is limiting The position of the fish, its value is 0.1, B is the volume of the simulated host, V is the simulated The volume of the fish, O Best That is, the optimal energy supply strategy for the plant in the iterative results.

[0090] like Figure 3 As shown in the figure, the present invention is a comparison chart of carbon emissions before and after the installation of the intelligent plant energy scheduling method with digital twin technology for a 100,000 square meter plant. It can be seen from the figure that the carbon emissions of the plant after the installation of the intelligent plant scheduling method are significantly reduced, which has the beneficial effect of reducing primary energy consumption and reducing carbon emissions.

[0091] An embodiment of the present invention also provides a device, including a memory, a processor, and a program stored in the memory and executable on the processor, characterized in that when the processor executes the program, the steps in the smart factory energy scheduling method based on digital twin technology as described in any one of the above items are implemented.

Claims

1. An intelligent plant energy dispatching system based on digital twin technology, characterized in that: include: The physical space module of the plant energy dispatching system, the digital space module of the plant energy dispatching system, the twin data service platform module, and the cloud platform module; the physical space module of the plant energy dispatching system is used to transmit physical data to the twin data service platform module and receive simulation data from the digital space module of the plant energy dispatching system; the digital space module of the plant energy dispatching system is used to receive data sent by the physical space module of the plant energy dispatching system through a wireless network and perform data mapping; the twin data service platform module is mainly used to collect data information from the physical space module of the plant energy dispatching system and the digital space module of the plant energy dispatching system, and send the corresponding data processing results to the cloud platform, the physical space module of the plant energy dispatching system, and the digital space module of the plant energy dispatching system; the cloud platform module is used to collect the data of the physical space module of the plant energy dispatching system, the digital space module of the plant energy dispatching system, and the twin data service platform as a whole, and then use the improved The fish optimization algorithm calculates the optimal energy supply strategy for the plant; among them, the improved The fish optimization algorithm consists of the following steps: (1) Establish the objective function; specifically: C=βP Grid O=min(Q E EF grid,OM )+min(βP Grid ) in, is the CO2 emissions of electricity generated by the production system, Q E is the total annual power supply of the plant system, EF grid,OM is the grid baseline CO2 emission factor, C is the economic cost, β is the distributed electricity price, P Grid It is the overall electricity consumption of the factory workshop; (2) Initialization Fish population position, maximum number of iterations and population size, calculate adaptive inertia weights; initialize The calculation formula for the fish population position is as follows: O i =lb+rand×(ub-lb) (1) Among them, O i is the position of individual i, that is, any system strategy generated by initialization; lb and ub are the lower and upper bounds of the search space, and rand is a random number between 0 and 1; exist An inertia weight w that changes with the number of iterations is added to the fish position update, according to The change of the update number in the fish optimization algorithm, the adaptive inertia weight formed by the number of iterations t is as follows: Among them, the inertia weight w represents a property that changes nonlinearly between [0,1]; (3) Based on the elite strategy of the sailfish optimization algorithm, the sailfish optimization algorithm formula is improved to calculate the randomly generated energy supply strategy; specifically: Where t is the current iteration number, The current best Fish individuals, that is, the currently obtained local optimal supply strategy, For the current random Individual fish, i.e., randomly generated energy provision strategies; (4) Calculate the local optimal solution; specifically: according to the previous generation The fish's position and the current host's position are compared. The fish moves in a small range around the host to determine whether to change the host. The calculation formula is as follows: Among them, O att yes A tentative move of the fish, O pre Indicates the previous generation The position of the fish, i.e., the local optimal supply strategy in the last search, randn is a normally distributed random number between 0 and 1; After a small move, The fish determines whether to change the host, and the calculation formula is as follows: If replaced, the calculation formula is as follows: H(i)=round(rand) Among them, H(i) determines The host of the fish parasite, the initial value is 0 or 1; if H(i) is equal to 0, it adsorbs whales, if H(i) is equal to 1, it adsorbs swordfish; round is the rounding function; and f(O att ) are respectively With O att The fitness value of (5) Use the whale algorithm to update the local optimal solution; specifically: k=rand×(a-1)+1 Where D represents the distance between the optimal position before the update and the current position, k is a random number between -1 and 1, a decreases linearly between [-2,1] during the iteration, and T is the maximum number of iterations; (6) Calculate the global optimal solution, i.e., the optimal energy supply strategy for the plant; specifically: B=2×V×rand-V Among them, A is The distance the fish moves is related to Fish is related to the host size, Fish factor C is limiting The position of the fish, its value is 0.1, B is the volume of the simulated host, V is the simulated The volume of the fish, O Best That is, the optimal energy supply strategy for the plant in the iterative results.

2. According to claim 1, a smart plant energy dispatching system based on digital twin technology is characterized in that: The connection relationship between the modules is set as follows: the physical space module of the plant energy dispatching system is connected to the digital space module of the plant energy dispatching system; the twin data service platform module is connected to the digital space module of the plant energy dispatching system and the physical space module of the plant energy dispatching system respectively; the twin data service platform module is connected to the cloud platform module.

Images