Energy-saving control method and equipment for temperature and humidity of textile workshop and medium
By using a long short-term memory network to reinforce cotton moisture regain and yarn breakage rate data in the textile workshop, and combining this with particle swarm optimization algorithm to optimize pump and fan speeds, the problems of moisture regain forgetting and yarn breakage rate impact in temperature and humidity control in the textile workshop were solved, achieving a dynamic balance between energy consumption optimization and production quality.
Patent Information
- Application Number
- CN202510989803.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-17
- Publication Date
- 2025-11-18
AI Technical Summary
Existing technologies for temperature and humidity control in textile workshops have not considered strengthening the memory of moisture regain rate and related yarn breakage rate, resulting in the forgetting or redundancy of historical information, which affects the energy consumption optimization effect of equipment such as water pumps and fans.
Long Short-Term Memory (LSTM) networks are used to enhance cotton moisture regain. Combined with yarn breakage rate data, the speed of water pumps and fans is optimized through particle swarm optimization algorithms to achieve precise temperature and humidity control and energy consumption optimization.
It improved the prediction accuracy of the dynamic curve of cold load/wet load, reduced the total energy consumption of the workshop, stabilized the yarn quality, and reduced abnormal fluctuations in yarn breakage rate.
Smart Images
Figure CN120969997A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of industrial intelligent control, and in particular to a textile workshop temperature and humidity energy-saving control method, device and medium. BACKGROUND
[0002] As a high energy consumption production scene, the temperature and humidity control of the textile workshop directly affects the yarn quality breakage rate and the energy consumption of the air conditioning system. The traditional control method relies on a single physical model, and the static temperature and humidity calculation based on the heat conduction formula; or a simple data-driven basic neural network to predict the load.
[0003] Firstly, the physical model does not fully utilize the long-term influence of the cotton regain rate, resulting in insufficient load prediction accuracy; secondly, the simple data-driven method lacks a memory reinforcement mechanism for the key variable of the regain rate, which is prone to prediction deviation due to historical information forgetting or redundancy, ultimately affecting the energy consumption optimization effect of devices such as water pumps and fans. In addition, the existing technology is not associated with the production quality indicator yarn breakage rate; at the same time, the speed optimization of water pumps and fans is often independent of the real-time temperature and humidity change curve, making it difficult to achieve minimum energy consumption at all times.
[0004] Through the above analysis, the problems and defects of the prior art are:
[0005] The temperature and humidity control of the textile workshop in the prior art does not consider the reinforcement of the regain rate memory and the association with the yarn breakage rate, resulting in prediction deviation due to historical information forgetting or redundancy, ultimately affecting the energy consumption optimization effect of devices such as water pumps and fans. SUMMARY
[0006] The embodiments of the present application provide a textile workshop temperature and humidity energy-saving control method, device and medium, which can solve the problem of the prior art that the temperature and humidity control of the textile workshop does not consider the reinforcement of the regain rate memory and the association with the yarn breakage rate, resulting in prediction deviation due to historical information forgetting or redundancy, ultimately affecting the energy consumption optimization effect of devices such as water pumps and fans.
[0007] In a first aspect, the embodiments of the present application provide a textile workshop temperature and humidity energy-saving control method, characterized in that the method comprises: collecting workshop temperature and humidity data, cotton regain rate, textile equipment operating parameters and yarn breakage rate data; performing missing value filling and normalization processing on the collected multi-source data to obtain a time series data set; inputting the time series data set into a long short-term memory network, reinforcing the cotton regain rate, and outputting a workshop cold load dynamic curve and a wet load dynamic curve for a future preset time length; based on the heat capacity parameters of the workshop and the moisture absorption characteristics of the cotton, combining the cold load dynamic curve and the wet load dynamic curve, calculating a temperature and humidity change curve; obtaining water pump physical model parameters and fan physical model parameters, taking the minimization of the total energy consumption of the workshop as an objective function, and solving the optimal water pump speed and fan speed according to the temperature and humidity change curve using a particle swarm optimization algorithm.
[0008] In an implementation form of the present application, the time series data set is input into a long short-term memory network, and the future preset time length of the workshop cold load dynamic curve and the wet load dynamic curve is output by reinforcing the cotton regain, specifically including: adding a cotton regain special input channel in the forget gate of the long short-term memory network; adjusting the forgetting proportion of the historical load data through the forget gate weight matrix and the bias vector according to the current cotton regain and the historical load characteristics; combining the historical load characteristics, and performing linear transformation through the input gate weight matrix and the bias vector according to the temperature and humidity data, the cotton regain and the textile equipment operation parameters input at the current moment, and outputting the forget gate value through the sigmoid activation function.
[0009] In an implementation form of the present application, the method further comprises: combining the historical load characteristics, and performing linear transformation through the input gate weight matrix and the bias vector according to the temperature and humidity data, the cotton regain and the textile equipment operation parameters input at the current moment, and outputting the input gate value through the sigmoid activation function.
[0010] In an implementation form of the present application, the method further comprises: multiplying the forget gate value and the memory unit at the last moment to obtain the historical load memory; multiplying the input gate value and the candidate memory unit to obtain the fused new load information; adding the historical load memory and the new load information to generate the memory unit at the current moment, and the memory unit at the current moment is used to output the future preset time length of the workshop cold load dynamic curve and the wet load dynamic curve.
[0011] In an implementation form of the present application, based on the heat capacity parameters of the workshop and the moisture absorption characteristics of the cotton, the temperature and humidity change curve is calculated combined with the cold load dynamic curve and the wet load dynamic curve, specifically including: collecting the moisture content on the surface of the cotton yarn through the humidity sensor, and calculating the water vapor amount absorbed or released by the cotton combined with the cotton regain; calculating the influence amount of the wall on the temperature of the workshop through the heat conduction formula based on the wall density, the wall specific heat capacity and the wall volume parameters; calculating the lag amount of the air temperature change through the heat capacity formula based on the air density, the air specific heat capacity and the workshop volume parameters; obtaining the temperature and humidity change curve by combining the water vapor amount, the influence amount and the lag amount, and the cold load dynamic curve and the wet load dynamic curve.
[0012] In an implementation form of the present application, the physical model parameters of the water pump and the physical model parameters of the fan are obtained, the optimal water pump speed and the optimal fan speed are solved by adopting the particle swarm optimization algorithm with the minimum total energy consumption of the workshop as the objective function, specifically including: taking the sum of the water pump power consumption and the fan power consumption as the minimum target, wherein the water pump flow and the speed are in a linear relationship, and the fan air volume and the speed are in a linear relationship; the water pump flow is constrained not to exceed the upper limit of the rated flow, and the fan air volume is constrained not to exceed the upper limit of the rated air volume.
[0013] In an implementation form of the present application, after the optimal water pump rotating speed and the fan rotating speed are solved by using the particle swarm optimization algorithm, the method further comprises: converting the optimal water pump rotating speed into a chilled water flow adjustment instruction by a water pump frequency converter, and converting the fan rotating speed into a supply air volume adjustment instruction by a fan frequency converter; and correcting the temperature and humidity setting range according to the yarn breakage rate.
[0014] In an implementation form of the present application, the temperature and humidity setting range is corrected according to the yarn breakage rate, and specifically comprises: when the yarn breakage rate exceeds a preset threshold, reducing the temperature and humidity fluctuation of the preset range; and when the yarn breakage rate is lower than the preset threshold, expanding the temperature and humidity fluctuation of the preset range.
[0015] In a second aspect, the embodiments of the present application further provide a textile workshop temperature and humidity energy-saving control device, which comprises at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: collect workshop temperature and humidity data, cotton regain, textile equipment operating parameters and yarn breakage rate data; perform missing value filling and normalization processing on the collected multi-source data to obtain a time series data set; input the time series data set into a long short-term memory network, and output a future preset time length of workshop cold load dynamic curve and wet load dynamic curve by strengthening the cotton regain; calculate a temperature and humidity change curve based on the workshop heat capacity parameters and the cotton moisture absorption characteristics, in combination with the cold load dynamic curve and the wet load dynamic curve; obtain water pump physical model parameters and fan physical model parameters, and solve optimal water pump rotating speed and fan rotating speed by using a particle swarm optimization algorithm according to the temperature and humidity change curve, with the minimization of total energy consumption of the workshop as an objective function.
[0016] In a third aspect, the embodiments of the present application further provide a non-volatile computer storage medium for energy-saving control of textile workshop temperature and humidity, which stores computer executable instructions, and the computer executable instructions are set to: collect workshop temperature and humidity data, cotton regain, textile equipment operating parameters and yarn breakage rate data; perform missing value filling and normalization processing on the collected multi-source data to obtain a time series data set; input the time series data set into a long short-term memory network, and output a future preset time length of workshop cold load dynamic curve and wet load dynamic curve by strengthening the cotton regain; calculate a temperature and humidity change curve based on the workshop heat capacity parameters and the cotton moisture absorption characteristics, in combination with the cold load dynamic curve and the wet load dynamic curve; obtain water pump physical model parameters and fan physical model parameters, and solve optimal water pump rotating speed and fan rotating speed by using a particle swarm optimization algorithm according to the temperature and humidity change curve, with the minimization of total energy consumption of the workshop as an objective function.
[0017] The energy-saving control method, device and medium for the temperature and humidity of a textile workshop provided by the embodiment of the application realize accurate control and energy consumption optimization of the temperature and humidity of the textile workshop through deep fusion of a physical model and data driving; based on the memory retention mechanism of the LSTM reinforced cotton moisture regain, the forgetting proportion of historical load data is dynamically adjusted, and the prediction accuracy of the future cold load / wet load dynamic curve is significantly improved; in combination with the temperature and humidity change curve, the rotating speed of the water pump / fan is optimized through the particle swarm algorithm, so that the total energy consumption of the workshop is reduced compared with the traditional method; the yarn breakage rate is introduced as the correction basis of the temperature and humidity setting range, the fluctuation range is reduced when the breakage rate exceeds the standard to stabilize the quality, and the fluctuation range is expanded when the breakage rate is stable to reduce the energy consumption, so that the dynamic balance between energy saving and production quality is realized, and the frequency of abnormal fluctuation of the yarn breakage rate is reduced. BRIEF DESCRIPTION OF DRAWINGS
[0018] The drawings described herein are used to provide further understanding of the application, constitute a part of the application, the illustrative embodiments of the application and the description thereof are used to explain the application, and do not constitute improper limitation on the application. In the drawings:
[0019] Figure 1 The flowchart of the energy-saving control method for the temperature and humidity of a textile workshop provided by the embodiment of the application;
[0020] Figure 2 The internal structure schematic diagram of the energy-saving control device for the temperature and humidity of a textile workshop provided by the embodiment of the application. DETAILED DESCRIPTION
[0021] In order to make the purpose, technical scheme and advantages of the application more clear, the technical scheme of the application will be described clearly and completely in combination with the specific embodiments of the application and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the application.
[0022] The energy-saving control method, device and medium for the temperature and humidity of a textile workshop provided by the embodiment of the application solve the problems that the temperature and humidity control of the textile workshop in the prior art has not considered to strengthen the memory of the moisture regain, and the prediction deviation is caused by the forgetting or redundancy of historical information, which finally affects the energy consumption optimization effect of the water pump, fan and other devices.
[0023] The technical scheme proposed by the embodiment of the application will be described in detail below with reference to the drawings.
[0024] Figure 1 The flowchart of the energy-saving control method for the temperature and humidity of a textile workshop provided by the embodiment of the application. As Figure 1As shown, the energy-saving control method for textile workshop temperature and humidity provided by the embodiment of the application specifically comprises the following steps:
[0025] Step 10: Collecting workshop temperature and humidity data, cotton moisture regain, textile equipment operation parameters and yarn breakage rate data.
[0026] In this step, the temperature and humidity data include internal and external temperature and humidity data of the workshop, and the textile equipment operation parameters include equipment operation power and the number of start-ups.
[0027] Step 20: Missing value filling and normalization processing are performed on the collected multi-source data to obtain a time series data set.
[0028] Step 30: The time series data set is input into a long short-term memory network, the cotton moisture regain is strengthened, and the workshop cold load dynamic curve and the wet load dynamic curve for a preset length of time in the future are output.
[0029] In this step, let t be the current time, t-1 be the previous time, and the key variables be defined as follows:
[0030] x t is the input vector at the current time, including temperature and humidity, moisture regain, equipment parameters, etc., with a dimension of dx; h t-1 is the hidden state at the previous time (dimension d h ); c t-1 is the memory unit at the previous time (dimension dc); W f ,b f : forgetting gate weight matrix (d h (dx+dh)) and bias vector (dh); Wi, bi: input gate weight matrix dh×(dx+dh)) and bias vector (dh); Wc~, bc~: candidate memory unit weight matrix (dc×(dx+dh)) and bias vector (dc).
[0031] As an optional embodiment, the time series data set is input into a long short-term memory network, the cotton moisture regain is strengthened, and the workshop cold load dynamic curve and the wet load dynamic curve for a preset length of time in the future are output. Specifically, it can comprise the following steps: step 301: adding a cotton moisture regain special input channel in the forgetting gate of the long short-term memory network; step 302: adjusting the forgetting proportion of historical load data through the forgetting gate weight matrix and the bias vector according to the current cotton moisture regain and the historical load characteristics; step 303: inputting the temperature and humidity data, the cotton moisture regain and the textile equipment operation parameters at the current time; step 304: combining the historical load characteristics, performing linear transformation through the input gate weight matrix and the bias vector, and outputting the forgetting gate value through the sigmoid activation function.
[0032] In this step, the forgetting gate value is calculated as follows:
[0033] f t = σ(W f · [x t ; h t-1 ] + b f )
[0034] Wherein, sigma is a sigmoid activation function (output range [0, 1]), [xt; ht-1] represents the vector spliced by xt and h t-1 f t represents the retention rate of historical memory (the value is closer to 1, the more retention).
[0035] As an optional embodiment, the method can further comprise: step 305: inputting the temperature and humidity data, the cotton regain and the textile equipment operation parameters according to the current time; step 306: combining the historical load characteristics, performing linear transformation through the input gate weight matrix and the bias vector, and outputting the input gate value through the sigmoid activation function.
[0036] In this step, the input gate value is calculated:
[0037] i t = sigma(W i · [x t ; h t-1 ] + b i )
[0038] i t represents the input proportion of the current new information (the value is closer to 1, the more input).
[0039] As an optional embodiment, the method can further comprise: step 307: multiplying the forgetting gate value with the memory unit of the last time to obtain the historical load memory; step 308: multiplying the input gate value with the candidate memory unit to obtain the fused new load information; step 309: adding the historical load memory and the new load information to generate the memory unit of the current time, and the memory unit of the current time is used to output the workshop cold load dynamic curve and the wet load dynamic curve of the future preset time length.
[0040] In this step, the candidate memory unit is generated:
[0041] c t ~ = tanh(W c ~· [x t ; h t-1 ] + bc~)
[0042] tanh is a hyperbolic tangent activation function (output range [-1, 1]), c t ~ represents the new load characteristics of the current input.
[0043] Current memory unit update:
[0044] c t =f t ⊙c t-1 +i t ⊙c t ~
[0045] Wherein, ⊙ is the element-by-element multiplication, c t Fusion of historical memory (ft⊙c t-1 ) and new information (it⊙c t ~), finally used for output cold / wet load dynamic curve.
[0046] Step 40: based on the heat capacity parameters of workshop and the moisture absorption characteristics of cotton, combined with the cold load dynamic curve and the wet load dynamic curve, the temperature and humidity change curve is calculated.
[0047] As an optional embodiment, based on the heat capacity parameters of workshop and the moisture absorption characteristics of cotton, combined with the cold load dynamic curve and the wet load dynamic curve, the temperature and humidity change curve can be calculated, which can specifically include: step 401: the moisture content on the surface of cotton yarn is collected by the humidity sensor, and the water vapor absorption or release of cotton is calculated combined with the moisture regain of cotton; step 402: based on the wall density, wall specific heat capacity, wall volume parameters, the influence of wall on workshop temperature is calculated by heat conduction formula; step 403: based on the air density, air specific heat capacity, workshop volume parameters, the hysteresis of air temperature change is calculated by heat capacity formula; step 404: the water vapor amount, influence and hysteresis are combined with the cold load dynamic curve and the wet load dynamic curve to obtain the temperature and humidity change curve.
[0048] In this step, the water vapor amount is calculated:
[0049] ΔM=ρ 棉 ·V 棉 ·(current moisture regain-equilibrium moisture regain)
[0050] Wherein, ρcotton is the density of cotton (kg / m 3 ), Vcotton is the volume of cotton in the workshop (m 3 ), and the equilibrium moisture regain can be looked up in the temperature and humidity table, GB / T 9995-1997 "Determination of moisture content and moisture regain of textile materials-oven drying method".
[0051] The influence of wall temperature (Fourier heat conduction law):
[0052]
[0053] Wherein, λ is the thermal conductivity of wall A is the wall area (m 2 ), δ is the wall thickness (m), Toutside / inside is the temperature in and outside the workshop (℃), and Δt is the time step (s).
[0054] Air temperature lag amount (heat capacity formula):
[0055] ΔT 空气 = Q 冷负荷 / m 空气 ·c 空气
[0056] Wherein, Q 冷负荷 is the dynamic curve value of the cooling load output by the LSTM (W), m 空气 = p 空气 ·V 车间 (Air mass, kg), c 空气 is the specific heat capacity of air (J / (kg·K)).
[0057] Synthesis of temperature and humidity change curve:
[0058] Temperature and humidity change curve = f (AM, Q 墙 , AT 空气 , cooling load curve, wet load curve)
[0059] By multivariate linear regression or physical model coupling, the above parameters are integrated into the time series temperature and humidity change curve {T(t), H(t)} t＝1 N .
[0060] Step 50: Obtain the water pump physical model parameters and the fan physical model parameters, and minimize the total energy consumption of the workshop as the objective function, according to the temperature and humidity change curve, and solve the optimal water pump speed and fan speed by using the particle swarm optimization algorithm.
[0061] In this step, the temperature physical model of the textile workshop is:
[0062]
[0063] Q p = Q dh + Q gh + Q d + Q g
[0064] Wherein, p is the air density; C is the specific heat capacity of air; V F is the volume of the workshop; n is the wall temperature rise coefficient; p W is the wall density; C W is the specific heat capacity of the wall; V W is the volume of the wall; T F is the temperature of the workshop; t is the time variable; Q s is the sensible heat of the supply air; Q h2 is the sensible heat of the secondary return air; Q JQHeat removal for textile machine; Q w Heat removal for maintenance structure; Q p Heat removal for exhaust air; Q dh Heat removal for ground exhaust air; Q gh Heat removal for process return air; Q d Heat removal for ground exhaust air; Q g Heat removal for process exhaust air,
[0065] Physical model of humidity for textile workshop:
[0066]
[0067] M is the humidity content of workshop; L x is the fresh air volume; L h1 is the primary return air volume; M2 is the supply air humidity content; L h2 is the secondary return air volume; M h2 is the secondary return air humidity content; m hc is the cotton moisture regain; L dh is the ground exhaust return air volume; M d is the ground exhaust air humidity content; L gh is the process return air volume; M g is the process exhaust air humidity content; L d is the ground exhaust air volume; L g is the process exhaust air volume.
[0068] Physical model of water pump:
[0069] W = ρ s W s
[0070] w s is the water pump flow rate; w e is the rated flow rate of water pump; N w is the water pump speed; N we is the rated speed of water pump; W is the water pump water injection volume; ρ s is the density of water.
[0071] Physical model of fan:
[0072]
[0073] L s is the fan supply air volume; L e is the rated supply air volume of fan; N l is the fan speed; N le is the rated speed of fan.
[0074] As an optional embodiment, the water pump physical model parameters and the fan physical model parameters are acquired, and a particle swarm optimization algorithm is used to solve optimal water pump rotating speed and fan rotating speed with minimization of total energy consumption of the workshop as an objective function. Specifically, the method can include: step 501: taking the sum of water pump power consumption and fan power consumption as a minimization target, wherein the water pump flow rate and the rotating speed are in a linear relationship, and the fan air volume and the rotating speed are in a linear relationship; step 502: restricting the water pump flow rate to be not more than an upper limit of a rated flow rate, and restricting the fan air volume to be not more than an upper limit of a rated air volume.
[0075] As an optional embodiment, after the particle swarm optimization algorithm is used to solve the optimal water pump rotating speed and the fan rotating speed, the method can further include: step 503: converting the optimal water pump rotating speed into a chilled water flow rate adjustment instruction through a water pump frequency converter, and converting the fan rotating speed into a supply air volume adjustment instruction through a fan frequency converter; and step 504: correcting a temperature and humidity setting range according to the yarn breakage rate.
[0076] As an optional embodiment, the temperature and humidity setting range is corrected according to the yarn breakage rate, and specifically, the method can include: step 5041: when the yarn breakage rate exceeds a preset threshold, reducing temperature and humidity fluctuation in a preset range; and step 5042: when the yarn breakage rate is lower than the preset threshold, expanding temperature and humidity fluctuation in the preset range. The above is an embodiment of the method of the present application.
[0077] In this step, the yarn breakage rate is an important indicator to measure the quality of textile production, which is closely related to the temperature and humidity environment of the workshop. Therefore, according to the actual situation of the yarn breakage rate to correct the temperature and humidity setting range, the purpose of energy saving and consumption reduction can be realized on the premise of ensuring product quality. The preset threshold is a yarn breakage rate standard value preset according to production experience and quality requirements. When the real-time monitored yarn breakage rate exceeds this preset threshold, it means that the current temperature and humidity environment may not be conducive to the production of yarn, which is easy to cause yarn breakage. In this case, the preset range of temperature and humidity fluctuation needs to be reduced. For example, the originally set temperature range is 25℃±2℃, and the humidity range is 60%±5%. When the yarn breakage rate exceeds the preset threshold, the temperature range can be reduced to 25℃±1℃, and the humidity range can be reduced to 60%±3%. By reducing the fluctuation amplitude of temperature and humidity, the influence of excessive temperature and humidity change on yarn can be reduced, and the probability of yarn breakage can be reduced, thereby improving the product quality. When the yarn breakage rate is lower than the preset threshold, it means that the current temperature and humidity environment can meet the production requirements, and the production quality of the yarn is relatively stable. At this time, the preset range of temperature and humidity fluctuation can be appropriately expanded to reduce the energy consumption of the air conditioning system. For example, the temperature range is expanded to 25℃±3℃, and the humidity range is expanded to 60%±7%. On the premise of ensuring that the quality of yarn is not affected, the temperature and humidity are allowed to fluctuate in a larger range, so that the air conditioning system does not need to be adjusted frequently, thereby reducing the energy consumption. In this way, the production quality can be guaranteed, and the energy saving goal can be realized.
[0078] Based on the same inventive concept, the embodiment of the present application also provides a textile workshop temperature and humidity energy-saving control device, the structure of which is shown in Figure 2 .
[0079] Figure 2 The internal structure of a textile workshop temperature and humidity energy-saving control device provided by the embodiment of the present application is shown in Figure 2 . The device comprises:
[0080] at least one processor 201;
[0081] and a memory 202 in communication connection with the at least one processor;
[0082] The memory 202 stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor 201 to enable the at least one processor 201 to: collect workshop temperature and humidity data, cotton regain, textile equipment operation parameters and yarn breakage rate data; perform missing value filling and normalization processing on the collected multi-source data to obtain a time series data set; input the time series data set into a long short-term memory network, and output a workshop cold load dynamic curve and a wet load dynamic curve for a future preset time length by strengthening the cotton regain; based on a workshop heat capacity parameter and a cotton moisture absorption characteristic, and in combination with the cold load dynamic curve and the wet load dynamic curve, calculate a temperature and humidity change curve; obtain water pump physical model parameters and fan physical model parameters, and take minimizing total energy consumption of the workshop as an objective function, and solve optimal water pump speed and fan speed according to the temperature and humidity change curve by using a particle swarm optimization algorithm.
[0083] Some embodiments of the present application provide a non-volatile computer storage medium for energy-saving control of a textile workshop temperature and humidity corresponding to Figure 1 The computer executable instructions are set to: collect workshop temperature and humidity data, cotton regain, textile equipment operation parameters and yarn breakage rate data; perform missing value filling and normalization processing on the collected multi-source data to obtain a time series data set; input the time series data set into a long short-term memory network, and output a workshop cold load dynamic curve and a wet load dynamic curve for a future preset time length by strengthening the cotton regain; based on a workshop heat capacity parameter and a cotton moisture absorption characteristic, and in combination with the cold load dynamic curve and the wet load dynamic curve, calculate a temperature and humidity change curve; obtain water pump physical model parameters and fan physical model parameters, and take minimizing total energy consumption of the workshop as an objective function, and solve optimal water pump speed and fan speed according to the temperature and humidity change curve by using a particle swarm optimization algorithm.
[0084] Each of the embodiments in the present application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each of the embodiments focuses on the difference from other embodiments. In particular, for the Internet of Things device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiments.
[0085] The system and medium provided by the embodiments of the present application are one-to-one corresponding to the method, and therefore, the system and medium also have similar beneficial technical effects to the method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the system and medium will not be described here.
[0086] Those skilled in the art will appreciate that embodiments of the application can be readily used as software, hardware, or a combination of software and hardware. In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.
[0087] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.
[0088] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.
[0089] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.
[0090] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.
[0091] The memory can include non-persistent memory and / or persistent memory, such as flash memory, readonly memory (ROM), and / or the like, in a computer-readable medium. The memory is an example of computer-readable media.
[0092] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.
[0093] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusions, so that a process, method, article or apparatus that includes a list of elements does not only include those elements, but also includes other elements not explicitly listed, or further includes elements inherent in such a process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.
[0094] The above only describes the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of the present application shall be included in the scope of claims of the present application.
Claims
1. A method for energy saving control of temperature and humidity in a textile plant, characterized in that, The method comprises: Collecting workshop temperature and humidity data, cotton regain, textile equipment operating parameters and yarn breakage rate data; Performing missing value filling and normalization processing on the collected multi-source data to obtain a time series data set; Inputting the time series data set into a long short-term memory network, reinforcing the cotton regain, and outputting a workshop cold load dynamic curve and a wet load dynamic curve for a preset length of time in the future; Based on the heat capacity parameters of the workshop and the moisture absorption characteristics of cotton, the cold load dynamic curve and the wet load dynamic curve are combined to calculate the temperature and humidity change curve; Obtain the water pump physical model parameters and the fan physical model parameters, take the minimization of the total energy consumption of the workshop as the objective function, and solve the optimal water pump speed and fan speed by using a particle swarm optimization algorithm according to the temperature and humidity change curve.
2. The energy-saving control method for temperature and humidity in a textile workshop according to claim 1, characterized in that, The time series data set is inputted into the long short-term memory network, the cotton regain is reinforced, and the workshop cold load dynamic curve and the wet load dynamic curve for a preset length of time in the future are outputted, specifically comprising: An input channel dedicated to the cotton regain is added to the forget gate of the long short-term memory network; According to the current cotton regain and historical load characteristics, the forgetting proportion of the historical load data is adjusted through a forgetting gate weight matrix and a bias vector; According to the temperature and humidity data, the cotton regain and the textile equipment operating parameters inputted at the current time; The historical load characteristics are combined, linear transformation is performed through an input gate weight matrix and a bias vector, and a forgetting gate value is outputted through a sigmoid activation function.
3. The energy-saving control method for temperature and humidity in a textile workshop according to claim 2, characterized in that, The method further comprises: According to the temperature and humidity data, the cotton regain and the textile equipment operating parameters inputted at the current time; The historical load characteristics are combined, linear transformation is performed through an input gate weight matrix and a bias vector, and an input gate value is outputted through a sigmoid activation function.
4. The energy-saving control method for temperature and humidity in a textile workshop according to claim 3, characterized in that, The method further comprises: The forgetting gate value is multiplied by the memory unit at the previous time to obtain historical load memory; The input gate value is multiplied by the candidate memory unit to obtain fused new load information; The historical load memory and the new load information are added to generate a current time memory unit, which is used to output the workshop cold load dynamic curve and the wet load dynamic curve for a preset length of time in the future.
5. The energy-saving control method for temperature and humidity in a textile workshop according to claim 1, characterized in that, The temperature and humidity change curve is calculated based on the heat capacity parameters of the workshop and the moisture absorption characteristics of cotton, and combined with the cold load dynamic curve and the wet load dynamic curve, specifically comprising: The moisture content on the surface of cotton yarn is collected by a humidity sensor, and the amount of water vapor absorbed or released by cotton is calculated based on the cotton regain; Based on the wall density, wall specific heat capacity and wall volume parameters, the influence of the wall on the temperature of the workshop is calculated through a heat conduction formula; Based on the air density, air specific heat capacity and workshop volume parameters, the hysteresis of air temperature change is calculated through a heat capacity formula; The water vapor amount, influence amount and hysteresis amount are combined with the cold load dynamic curve and the wet load dynamic curve to obtain the temperature and humidity change curve.
6. The energy-saving control method for temperature and humidity in a textile mill according to claim 1, characterized in that, The water pump physical model parameters and the fan physical model parameters are obtained, the minimization of the total energy consumption of the workshop is taken as the objective function, and the optimal water pump speed and fan speed are solved by using a particle swarm optimization algorithm. The sum of water pump power consumption and fan power consumption is taken as a minimum target, wherein the water pump flow rate is linearly related to the rotating speed, and the fan air volume is linearly related to the rotating speed; The water pump flow rate is constrained to be no more than an upper limit of a rated flow rate, and the fan air volume is constrained to be no more than an upper limit of a rated air volume.
7. The energy-saving control method for temperature and humidity in a textile mill according to claim 1, characterized in that, After the optimal water pump rotating speed and the fan rotating speed are solved by using the particle swarm optimization algorithm, the method further comprises: The optimal water pump rotating speed is converted into a chilled water flow rate adjustment instruction by a water pump frequency converter, and the fan rotating speed is converted into a supply air volume adjustment instruction by a fan frequency converter; According to the yarn breakage rate, the temperature and humidity setting range is corrected.
8. The energy-saving control method for temperature and humidity in a textile workshop according to claim 7, characterized in that, The temperature and humidity setting range is corrected according to the yarn breakage rate, and specifically comprises: When the yarn breakage rate exceeds a preset threshold, the temperature and humidity fluctuation of a preset range is reduced; When the yarn breakage rate is lower than the preset threshold, the temperature and humidity fluctuation of the preset range is expanded.
9. A textile plant temperature and humidity energy saving control device, characterized by, The device comprises: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: collect workshop temperature and humidity data, cotton regain, textile equipment operating parameters and yarn breakage rate data; perform missing value filling and normalization processing on the collected multi-source data to obtain a time series data set; input the time series data set into a long short-term memory network, and output a workshop cold load dynamic curve and a wet load dynamic curve for a future preset length of time by reinforcing the cotton regain; based on the workshop heat capacity parameters and the cotton moisture absorption characteristics, and in combination with the cold load dynamic curve and the wet load dynamic curve, calculate a temperature and humidity change curve; obtain water pump physical model parameters and fan physical model parameters, take the minimization of the total energy consumption of the workshop as an objective function, and solve the optimal water pump rotating speed and the fan rotating speed by using a particle swarm optimization algorithm according to the temperature and humidity change curve.
10. A non-transitory computer storage medium storing computer-executable instructions for energy saving control of temperature and humidity in a textile plant, the computer-executable instructions comprising: The computer executable instructions are set to: collect workshop temperature and humidity data, cotton regain, textile equipment operating parameters and yarn breakage rate data; perform missing value filling and normalization processing on the collected multi-source data to obtain a time series data set; input the time series data set into a long short-term memory network, and output a workshop cold load dynamic curve and a wet load dynamic curve for a future preset length of time by reinforcing the cotton regain; based on the workshop heat capacity parameters and the cotton moisture absorption characteristics, and in combination with the cold load dynamic curve and the wet load dynamic curve, calculate a temperature and humidity change curve; obtain water pump physical model parameters and fan physical model parameters, take the minimization of the total energy consumption of the workshop as an objective function, and solve the optimal water pump rotating speed and the fan rotating speed by using a particle swarm optimization algorithm according to the temperature and humidity change curve.