Energy-saving monitoring system for assembled refrigeration room based on data analysis

Abstract

The application discloses an assembled refrigeration machine room energy-saving monitoring system based on data analysis, and relates to the technical field of energy-saving control.The system comprises an interval module, an excitation module, an identification module and a calculation module.The interval module is used for dividing the machine room space into multiple monitoring intervals and binding the intervals with structural units.The excitation module is used for applying power disturbance to the structural units to obtain structural excitation data.The identification module is used for generating a thermal influence coefficient matrix according to the excitation data and the temperature change of adjacent monitoring intervals.The calculation module is used for calculating blind area temperature based on the thermal influence coefficient matrix, structural energy consumption data and adjacent interval temperature, and outputting estimated temperature and covariance.The application divides the machine room space into a three-dimensional grid through the interval module, and binds each monitoring interval with a functional node in the machine room structure, so that a temperature monitoring grid with a space-structure correspondence is formed, which not only improves the spatial expression accuracy of monitoring data, but also provides structured support for the positioning of blind area positions and temperature compensation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of energy-saving control, in particular to an assembled refrigeration machine room energy-saving monitoring system based on data analysis. BACKGROUND

[0002] In modern building energy consumption management, as an energy-intensive area, the accurate monitoring of temperature distribution and dynamic adjustment based on heat load in the refrigeration machine room are the key paths to achieve efficient energy saving. Although the assembled refrigeration machine room has the advantages of rapid construction and standard module deployment, it also introduces new monitoring challenges due to its preset structure and compact space arrangement.

[0003] Under the assembled wiring structure, it is difficult to directly lay temperature sensors in some pipeline areas, heat source nodes, or end return water positions due to structural obstruction, concentrated wiring, or physical limitations, forming multiple monitoring blind areas. The existence of these blind areas can easily lead to the inability of the system to perceive the local heat distribution state, thereby affecting the accuracy of overall energy consumption adjustment.

[0004] After searching, a Chinese patent (publication number: CN116007122A) discloses an efficient refrigeration machine room energy-saving monitoring system based on data analysis. The patent includes an energy-saving monitoring platform, which is communicatively connected with an energy consumption monitoring module, a production capacity optimization module, an energy consumption optimization module, a parameter adjustment module, and a storage module. The energy consumption monitoring module is used to monitor and analyze the energy consumption of the refrigeration machine room. The production capacity optimization module is used to optimize and analyze the production capacity of the refrigeration machine room and obtain the production capacity characteristic parameters of the space interval. The production capacity characteristic parameters of the space interval are sent to the energy-saving monitoring platform.

[0005] The existing scheme mainly uses linear compensation or empirical models for temperature estimation in blind areas. It has poor ability to combine the spatial layout, energy consumption state, and heat diffusion trend of the assembled structure itself, and it is difficult to identify external environmental disturbances or perform dynamic adjustment. Therefore, the present application proposes an assembled refrigeration machine room energy-saving monitoring system based on data analysis. SUMMARY

[0006] The purpose of the present application is to provide an assembled refrigeration machine room energy-saving monitoring system based on data analysis to solve the problems mentioned in the background.

[0007] The present application can be implemented by the following technical scheme: an assembled refrigeration machine room energy-saving monitoring system based on data analysis, comprising: an interval module, an excitation module, an identification module, a processing module, and an energy-saving control module.

[0008] The interval module is used to divide the machine room space into multiple monitoring intervals and bind them with structural units.

[0009] The excitation module is configured to apply a power disturbance to the structural unit and obtain structural excitation data;

[0010] The identification module is configured to generate a thermal influence coefficient matrix according to the excitation data and temperature changes of adjacent monitoring intervals;

[0011] The calculation module is configured to calculate a blind area temperature based on the thermal influence coefficient matrix, structural energy consumption data and adjacent interval temperatures, and output an estimated temperature and a covariance;

[0012] The processing module is configured to judge the confidence of the estimated temperature, and trigger an update of the thermal influence coefficient matrix when a preset condition is not met;

[0013] The energy-saving control module is configured to adjust the operating parameters of the refrigeration system according to the space temperature field and the load prediction result, and achieve an energy-saving operation goal.

[0014] Further technical improvements of the present application are that the calculation module judges whether to correct the estimated temperature of the current blind area based on the temperature change sequence of the standard area, the external environment change trend and the interference duration in the case that the standard area adjacent to the blind area is disturbed by the external environment.

[0015] Further technical improvements of the present application are that the judgment method of the calculation module comprises the following steps:

[0016] A1, edge area identification: according to the monitoring interval and the structure space binding table output in the interval module, the monitoring area directly contacted with the external structure boundary is identified as a candidate disturbance sensitive area;

[0017] A2, temperature sequence analysis: for the standard area adjacent to the blind area, the temperature change sequence in the current estimation period is extracted, and a temperature rise trend model is constructed;

[0018] A3, external environment linkage judgment: the environmental parameters (such as external radiation intensity, external air temperature, etc.) in the corresponding period are synchronously obtained, and are associated with the temperature change of the standard area;

[0019] A4, if the temperature rise rate of the standard area in a unit time is significantly higher than the historical steady-state average value, and there is no corresponding structure power output fluctuation, the standard area is marked as a "potential external disturbance area", and the interference duration is recorded.

[0020] Further technical improvements of the present application are that the processing module enters the following operations after receiving the estimated blind area temperature and the covariance:

[0021] B1, associated blind area identification:

[0022] b11, obtaining the standard area which has been marked as a "potential external disturbance area";

[0023] b12, judge whether its adjacent blind area is the estimated blind area j, if yes, mark the corresponding blind area as a candidate for correction;

[0024] B2, correction condition judgment:

[0025] If the following two conditions are met:

[0026] The standard area marked as "potential external disturbance area" has a temperature rise time greater than the preset temperature rise time threshold;

[0027] The covariance ∑ of the current blind area estimated temperature j,j is less than the upper limit of confidence;

[0028] Then enter the estimated temperature correction process;

[0029] B3, standard area temperature rise calculation:

[0030] Calculate the standard area temperature change ΔT std by the formula: ΔT std = T std,now -T std,base ;

[0031] In the formula, T std,now is the real-time temperature value of the standard area at the current time, collected by the temperature sensor; T std,base is the reference steady-state temperature value of the standard area under stable external environment and undisturbed state, which is usually the baseline temperature measured under historical statistical average or low disturbance condition;

[0032] B4, blind area estimated temperature correction:

[0033] Adjust the estimated temperature to obtain the corrected estimated temperature

[0034] α∈(0,1), is the disturbance correction coefficient, which can be set according to the disturbance duration, for example:

[0035] If the disturbance duration is more than 15 minutes, set α = 0.8;

[0036] If the disturbance duration is 5-15 minutes, set α = 0.5;

[0037] If the disturbance duration is less than 5 minutes, do not trigger correction;

[0038] B5, output and recovery mechanism:

[0039] b51, replace the original estimated temperature with the corrected estimated temperature Input value energy saving control module

[0040] b52, if the subsequent judgment interference state is eliminated, the original estimated temperature is restored And update the blind area state marker.

[0041] The further technical improvement of the application is that when the closed loop structure is formed by a plurality of standard areas with temperature rise exceeding the threshold outside the monitoring blind area, the processing module calculates the average temperature rise of the closed loop area, and corrects the current estimated temperature of the blind area based on the temperature rise to improve the accuracy of temperature estimation. The specific correction method comprises the following steps:

[0042] Z1, closed loop boundary identification;

[0043] The processing module traverses the peripheral area of each blind area j based on the spatial topology structure and the adjacency matrix of the monitoring interval;

[0044] If the blind area j is surrounded by a plurality of adjacent standard areas, and the temperature rise of the standard area surrounding the blind area j is greater than the preset temperature rise threshold, the processing module determines that there is a closed high-temperature boundary structure outside the blind area j;

[0045] Z2, boundary area temperature rise amount statistics;

[0046] The processing module extracts the temperature rise of all standard areas forming the closed loop, and calculates the average temperature rise

[0047] Z3, blind area temperature correction;

[0048] Using the formula: The estimated temperature of the current blind area Is offset to obtain the corrected estimated temperature of the current blind area

[0049] In the formula, β ∈ (0.5, 1.0) is the closed loop isothermal correction coefficient, which is dynamically adjusted according to the boundary strength and temperature rise consistency;

[0050] Z4, output and state marker;

[0051] The corrected estimated temperature Replaces the original estimated temperature Input the energy saving control module, mark the current blind area j as "closed loop correction state", and record the correction value and closed loop identification source for subsequent trend analysis and model adjustment.

[0052] The further technical improvement of the present application is that the processing module corrects the estimated temperature of the blind area according to the temperature difference between the distribution structures if multiple arc-shaped distribution structures with similar temperature are identified in the standard area when the outside of the blind area does not form a closed loop.

[0053] The further technical improvement of the present application is that the method for correcting the estimated temperature by the processing module comprises:

[0054] Y1, the processing module first determines whether multiple standard monitoring areas distributed in different directions exist outside the blind area, and analyzes the temperature changes of these areas respectively;

[0055] When two or more consecutive standard areas in at least two spatial directions are identified, the temperature of each area has an upward trend exceeding the set temperature rise threshold in the current estimation period, and these standard areas cannot form a closed blind area by being continuously enclosed by standard areas, it is determined that the blind area is in a non-closed loop structure condition;

[0056] Y2, the processing module further analyzes the spatial distribution form of the temperature rise areas to determine whether it conforms to the heat diffusion trend;

[0057] Y3, the processing module selects standard monitoring areas with similar temperature in the candidate arc-shaped area to form an arc-shaped distribution structure set, and the judgment basis includes:

[0058] y31, the temperature rise amount difference of multiple standard areas is less than a preset difference threshold;

[0059] y32, the spatial arrangement forms a visible arc line or a gradual curve;

[0060] y33, the distance between the areas and the temperature change trend meet the expected direction of heat diffusion;

[0061] Y4, the processing module combines the position relationship of the blind area relative to each arc-shaped structure, and determines the dominant direction of temperature change according to the temperature difference along the arc-shaped path in the multiple identified arc-shaped structures;

[0062] On this basis, according to the relative geometric position of the blind area in the arc-shaped structure, the average or weighted average of the temperature difference in multiple arc-shaped directions is used to correct the current estimated temperature in the direction.

[0063] Compared with the prior art, the present application has the following beneficial effects:

[0064] The application divides the machine room space in three-axis directions of x, y and z by a "interval module" to form a temperature monitoring grid with a space-structure correspondence relationship, which not only improves the spatial expression accuracy of monitoring data, but also provides structured support for the positioning and temperature compensation of blind area positions, and solves the ambiguity problem of traditional methods in spatial thermal field modeling.

[0065] Moreover, by fusing the thermal influence coefficient matrix output by the "recognition module", the blind area estimation model constructed by the "calculation module", and the confidence evaluation and correction strategy of the "processing module", the application can dynamically estimate temperature data in the sensorless area, and perform multi-round correction according to the estimation error, external environmental interference or thermal diffusion structure characteristics. Especially under the condition that the blind area is not closed-loop or multi-directional thermal interference, the estimation amplitude can be automatically constructed and offset corrected according to the arc-shaped temperature distribution trend, which significantly improves the stability and reliability of the estimation.

[0066] On the other hand, the application uses the estimated blind area temperature and the measured temperature of the standard area together to generate a full-space temperature field, and uses it as input to drive the "energy-saving control module" to dynamically adjust the outlet water temperature of the water chiller unit, the frequency of the main pump / terminal water pump, the opening degree of the water valve and air valve, etc. When the blind area estimation is not reliable, the system automatically limits the adjustment range or switches to a safe operation mode, ensuring the safety of system operation while minimizing energy consumption. This closed-loop control mechanism significantly improves the accuracy and response flexibility of the energy-saving strategy, and is suitable for various types of prefabricated building energy systems. BRIEF DESCRIPTION OF DRAWINGS

[0067] In order to facilitate the understanding of those skilled in the art, the application will be further described below with reference to the accompanying drawings.

[0068] Figure 1 The figure shows the external structure of the application. DETAILED DESCRIPTION

[0069] In order to further illustrate the technical means and effects adopted by the application to achieve the predetermined invention purpose, the specific embodiments, structures, features and effects of the application are described in detail below with reference to the accompanying drawings and preferred embodiments.

[0070] Example 1

[0071] Please refer to Figure 1 The application provides an energy-saving monitoring system for prefabricated refrigeration machine rooms based on data analysis, which includes an interval module, an excitation module, a recognition module, a processing module and an energy-saving control module.

[0072] The interval module is used to build the space monitoring basic framework of the refrigeration machine room, determine the position of each monitoring interval in the three-dimensional space, and bind it with the specific machine room structure unit, which is used for subsequent load excitation, thermal influence identification and virtual estimation module. The association support of structure data and space temperature data;

[0073] When working, input:

[0074] BIM model or laser scanning data, providing machine room structure unit coordinate information;

[0075] Identification and location of machine room structure units (such as pipes, heat source equipment, and end return water outlets);

[0076] Processing:

[0077] 1. Divide the machine room space into multiple three-dimensional monitoring intervals along the x, y and z directions; the monitoring interval includes a standard area with sensor collection capability and a blind area that cannot be equipped with sensors due to structural limitations; among them, temperature sensors are set in the standard area to collect real-time basic temperature data of the area, and the collected basic temperature data is used as the observation basis data input in the blind area temperature estimation process to realize the reconstruction and dynamic update of the blind area temperature field;

[0078] 2. Based on the distance relationship between the structure coordinates and the center of gravity of the monitoring interval, complete the spatial binding of the monitoring interval and the structure unit;

[0079] 3. Output the mapping relationship table corresponding to the interval number and the machine room structure unit number;

[0080] Output:

[0081] 1. Monitoring interval space grid S(x, y, z);

[0082] 2. Monitoring interval-structure unit binding table;

[0083] The excitation module is used to actively apply power disturbance to induce changes in the thermal behavior of the structure unit, and then provide data basis for thermal influence relationship modeling through the temperature response of adjacent areas, playing the role of "data-driven identification exciter";

[0084] When working, input:

[0085] 1. Monitoring interval-structure unit binding table, which clearly indicates the monitoring interval of the target structure unit;

[0086] 2. Excitation task instructions, including target structure unit ID, excitation power increment, duration, etc.

[0087] Processing:

[0088] 1. Apply step load change (±10-30% power) to target structure unit (e.g. pump, chiller, heat source), control time is generally 2-5 minutes;

[0089] 2. Record structure unit ID, excitation amplitude, start time, end time, etc. during excitation, form event log;

[0090] Output:

[0091] 1. Excitation event log (contains structure unit ID, Δpower, timestamp);

[0092] 2. Identification module is used to calculate the heat transfer relationship between structure and space temperature according to the energy input of excitation source and the temperature change of adjacent monitoring interval, output heat influence coefficient matrix, provide quantifiable modeling parameters for blind area temperature estimation;

[0093] When working, input:

[0094] 1. Excitation event log;

[0095] 2. Real-time temperature sequence of adjacent monitoring intervals before and after excitation;

[0096] 3. Three-dimensional space coordinate matrix;

[0097] Processing:

[0098] 1. Associate and pair structure excitation power change ΔP with adjacent area temperature change ΔT;

[0099] 2. Use recursive least squares algorithm (RLS) to build input-output model;

[0100] 3. Identify the heat influence weight of each structure on multiple intervals, generate coefficient matrix K;

[0101] Output:

[0102] 1. Heat influence coefficient matrix K, and Indicates that there are m structure units (such as heat source equipment, pipe sections, etc.) in the corresponding machine room, and there are n space monitoring intervals; and K ij Indicates the unit heat influence ability of machine room equipment i on monitoring interval j;

[0103] 2. Confidence index CI of heat influence coefficient matrix K K*j Such as covariance or confidence interval;

[0104] The calculation module is used to solve the problem of blind area temperature monitoring that cannot be equipped with sensors, and combines structure energy consumption and adjacent interval temperature to calculate the real-time temperature of the blind area through the heat influence matrix, as one of the basic input data for energy saving monitoring;

[0105] Its work, input:

[0106] 1, the heat impact coefficient matrix K;

[0107] 2, the real-time running energy consumption data of the structural unit (such as power, current, running time);

[0108] 3, the temperature of the monitoring interval adjacent to the target blind area;

[0109] Processing:

[0110] 1, construct a state estimation model based on the heat impact model;

[0111] 2, use extended Kalman filter (EKF) to dynamically estimate the temperature of the blind area;

[0112] 3, output the estimated temperature and its covariance, used to reflect the prediction uncertainty;

[0113] Output:

[0114] 1, the estimated temperature and the covariance matrix ∑ j (t);

[0115] The processing module is used to determine the credibility of the estimated temperature output by the virtual temperature estimation processor, and decide whether to use the temperature value for energy-saving control strategy generation, or whether to start the auxiliary correction and model correction process, forming the closed-loop adaptive adjustment ability of the system;

[0116] The processing module also undertakes the generation and issuance of energy-saving control instructions, ensuring that the overall operation of the refrigeration machine room can be optimized even under the premise that part of the blind area has no sensor;

[0117] Its work, input:

[0118] 1, the estimated temperature

[0119] 2, the covariance matrix ∑ j (t), reflecting the uncertainty of the estimated temperature;

[0120] 3, the confidence index CI K*j of the heat impact coefficient matrix K;

[0121] Processing:

[0122] 1, confidence calculation: based on the jth diagonal element ∑ j,j (t) of the error covariance matrix ∑ j (t) of the estimated temperature , calculate its standard deviation

[0123] The following conditions are judged:

[0124] σ j (t)≤σ max , and CI K*j ≤CI max ; wherein, σ max and CI max are respectively the maximum acceptable uncertainty standards preset by the system;

[0125] If both conditions are met, the confidence is defined as "trusted", otherwise as "untrusted";

[0126] 2. Confidence response logic:

[0127] When the confidence is "trusted":

[0128] The estimated temperature is taken as an effective input parameter, which is passed to the energy-saving optimization algorithm module (such as the chilled water unit energy efficiency control, fan-pump collaborative strategy module), and the downstream model keeps the estimated temperature and the measured temperature as equal weight processing;

[0129] When the confidence is "untrusted":

[0130] The participation weight of the estimated temperature is set to λ (0 < λ < 1), that is, its influence is down-weighted in the system;

[0131] In this embodiment, the system scheduling layer generates a mobile thermal imager inspection task to control the thermal image acquisition device to go to the corresponding monitoring interval;

[0132] After obtaining the thermal image temperature T IR,j (t), the error is evaluated with the estimated temperature , if the error between the two is greater than the preset error threshold, the thermal image temperature T IR,j (t) is used to replace the current estimated temperature and trigger an update calculation of the thermal influence coefficient matrix K to correct the thermal influence coefficient matrix K.

[0133] Specifically, the steps of updating the thermal influence coefficient matrix K calculation include:

[0134] Collecting current structure energy consumption data, including the power, running time and other parameters of the bound structure unit at the current time point;

[0135] Obtaining the inspection measured temperature value and taking it as the corrected actual temperature;

[0136] The energy consumption data and the measured temperature form a sample pair to constitute the input and output data required for thermal influence modeling;

[0137] Recursive least square method is called to update the heat influence coefficient matrix K based on the current sample;

[0138] The corrected heat influence coefficient matrix K is generated to replace the original matrix for further temperature estimation;

[0139] The step of correcting the heat influence coefficient matrix K includes:

[0140] It is determined whether the error between the estimated temperature of the blind area and the measured temperature during the inspection exceeds the error threshold;

[0141] When the error exceeds the error threshold, it is considered that the original temperature model estimation is inaccurate, and the model correction process is entered;

[0142] The measured temperature is used to replace the current estimated value, and the point is marked as a "calibration data point";

[0143] Based on the calibration data, the corresponding parameters in the heat influence coefficient matrix K are updated to correct the local parameters;

[0144] After completing the parameter correction, the temperature of the blind area is re-estimated, and the new result is transmitted to the energy-saving control system for use;

[0145] The energy-saving control module is based on the full-space temperature field (including the measured and estimated fusion results), combined with the cold load prediction model and the energy efficiency curve of each device, to dynamically adjust the following parameters:

[0146] The outlet water temperature set value of the chiller;

[0147] The frequency or flow rate of the main pump and the terminal water pump;

[0148] The opening of the air conditioning terminal air valve or water valve;

[0149] The purpose of the control target is to keep the temperature of each monitoring area in the comfort interval to minimize the overall energy consumption. When the system detects that the estimated value of the blind area temperature is not reliable enough, it will tighten the adjustment range or switch to the safety mode operation;

[0150] The cold load prediction model refers to a time series prediction model constructed based on historical operation data, indoor and outdoor temperature and humidity trends, personnel activity patterns, etc., used to predict the change in cooling demand in a short period in advance;

[0151] The energy efficiency curve refers to the relationship function between unit energy consumption and performance output of the chiller, water pump and other devices under different load conditions, which is usually obtained by factory test or field calibration;

[0152] The estimated fusion result refers to the virtual temperature data obtained by the blind area temperature estimation algorithm, which is used to construct a more complete spatial temperature field after weighted fusion with the measured temperature;

[0153] The control target of the energy-saving control module is to minimize the overall energy consumption of the system while maintaining the temperature of each monitoring area within the comfortable control interval (e.g., 22-26°C), thereby improving operational efficiency. When the system detects that the confidence level of the estimated temperature of the blind area is insufficient (e.g., the estimated standard deviation exceeds a pre-set threshold or the thermal influence model deviation is significant), the control module will automatically trigger a degradation strategy, which specifically includes:

[0154] Adjusting the tightening range, i.e., reducing the response range of the control variable, to avoid over-reliance on the estimated value;

[0155] Or switching to a safe mode of operation, i.e., using conservative control settings to ensure stable temperature control in critical areas until the estimated results recover to a confidence level.

[0156] The calculation module determines whether to correct the estimated temperature of the current blind area based on the temperature variation sequence of the standard area, the external environment variation trend, and the duration of the disturbance in the vicinity of the blind area. The judgment method includes the following steps:

[0157] A1, Edge area identification: According to the monitoring area and structure space binding table output by the interval module, identify the monitoring area directly contacting the external structure boundary as the candidate disturbance sensitive area;

[0158] A2, Temperature sequence analysis: For the standard area adjacent to the blind area, extract the temperature variation sequence in the current estimation period, and construct a temperature rise trend model;

[0159] A3, External environment linkage judgment: Synchronously acquire the environmental parameters (such as external radiation intensity, external air temperature, etc.) in the corresponding period, and correlate them with the temperature variation of the standard area;

[0160] A4, If the temperature rise rate of the standard area in a unit time is significantly higher than the historical steady-state average value, and there is no corresponding structure power output fluctuation, mark the standard area as "potential external disturbance area", and record the disturbance duration.

[0161] After receiving the estimated blind area temperature and covariance, the processing module enters the following operations:

[0162] B1, Blind area identification:

[0163] b11, Obtain the standard area that has been marked as "potential external disturbance area";

[0164] b12, Determine whether its adjacent blind area is the estimated blind area j, if so, mark the corresponding blind area as the candidate correction object;

[0165] B2, Correction condition judgment:

[0166] If the following two conditions are met:

[0167] The standard area marked as "potentially subject to external disturbance" has a continuous temperature rise time that exceeds the preset temperature rise time threshold.

[0168] Covariance ∑ of current blind zone estimated temperature j,j (t) is less than the upper confidence level;

[0169] Then proceed to the estimated temperature correction process;

[0170] B3. Calculation of temperature rise in standard area:

[0171] Through the formula: ΔT std =T std,now -T std,base Calculate the temperature change ΔT in the standard region. std ;

[0172] In the formula, T std,now The real-time temperature value of the standard area at the current moment is collected by a temperature sensor; T std,base It is the reference steady-state temperature value of the standard area under stable and undisturbed external environment conditions, usually the historical statistical average or the baseline temperature measured under low disturbance conditions in the area.

[0173] B4. Blind Zone Estimated Temperature Correction:

[0174] For estimating temperature Adjust the offset to obtain the corrected estimated temperature.

[0175] α∈(0,1) is the perturbation correction coefficient, which can be set according to the duration of the perturbation, for example:

[0176] The disturbance lasts for more than 15 minutes, and we set α = 0.8;

[0177] The duration of the disturbance is 5-15 minutes, and we assume α = 0.5.

[0178] If the duration of the disturbance is less than 5 minutes, no correction will be triggered.

[0179] B5. Output and Recovery Mechanism:

[0180] b51. The corrected estimated temperature Replace the original estimated temperature Input value energy-saving control module;

[0181] b52. If the interference is subsequently determined to be eliminated, the original estimated temperature will be used again. And update the blind spot status marker;

[0182] In this embodiment, the j = 5th blind area, adjacent to the standard area std = 4;

[0183] The time period is 10:00-11:00, which is a high-intensity period of solar radiation;

[0184] Structural unit state: the cold water pipe section corresponding to the blind area 5 has no significant power fluctuation in this period;

[0185] External environment changes: external radiation intensity increases from 400 W / m 2 to 800 W / m 2 ; the external air temperature rises by 2.1℃; the duration of the influence of sunlight exceeds 12 minutes;

[0186] That is, the current temperature T std,now of the standard area = 29.6℃; the historical steady-state reference temperature (under the condition of no external disturbance) T std,base = 27.1℃;

[0187] The temperature rise of the standard area is obtained: ΔT std = T std,now -T std,base = 2.5℃;

[0188] The disturbance duration is 12 minutes, which is between 5-15 minutes, so the disturbance correction coefficient α = 0.5 is set by looking up the table;

[0189] The current estimated temperature of the 5th blind area is:

[0190] According to the correction formula

[0191] Finally, the corrected temperature is used for the energy-saving control logic of this period;

[0192] The original estimated temperature is no longer used as a control input;

[0193] The system marks this blind area as "correcting" state, and will return to the original model estimation path after the subsequent disturbance is removed.

[0194] Embodiment 2

[0195] The prefabricated refrigeration machine room energy-saving monitoring system based on data analysis, characterized in that it comprises:

[0196] An interval module for dividing the machine room space into multiple monitoring intervals and binding with the structural units;

[0197] An excitation module for applying power disturbance to the structural units and obtaining structural excitation data;

[0198] The identification module is configured to generate a thermal influence coefficient matrix according to the excitation data and temperature changes of adjacent monitoring intervals;

[0199] The calculation module is configured to calculate a blind area temperature based on the thermal influence coefficient matrix, structure energy consumption data, and adjacent interval temperatures, and output an estimated temperature and a covariance;

[0200] The processing module is configured to judge a confidence level of the estimated temperature and trigger an update of the thermal influence coefficient matrix when a preset condition is not met;

[0201] The energy-saving control module is configured to adjust operation parameters of a refrigeration system according to a space temperature field and a load prediction result, and achieve an energy-saving operation goal.

[0202] When a plurality of standard areas with temperature rises exceeding a threshold value form a closed loop structure outside the monitoring blind area, the processing module calculates an average temperature rise of the closed loop area, and corrects a current estimated temperature of the blind area based on the temperature rise, so as to improve the accuracy of temperature estimation. The specific correction method includes the following steps:

[0203] Z1, closed loop boundary identification;

[0204] The processing module traverses a peripheral area of each blind area j based on a spatial topology structure and an adjacency matrix of the monitoring interval;

[0205] If the blind area j is surrounded by a plurality of adjacent standard areas, and a temperature rise of the standard area surrounding the blind area j is greater than a preset temperature rise threshold value, the processing module determines that there is a closed high-temperature boundary structure outside the blind area j;

[0206] Z2, boundary area temperature rise amount statistics;

[0207] The processing module extracts temperature rises of all standard areas forming the closed loop, and calculates an average temperature rise thereof

[0208] Z3, blind area temperature correction;

[0209] Using the formula: The current blind area estimated temperature is offset to obtain a corrected estimated temperature of the current blind area

[0210] In the formula, β ∈ (0.5, 1.0) is a closed loop isothermal correction coefficient, which is dynamically adjusted according to boundary strength and temperature rise consistency;

[0211] Z4, output and state marking;

[0212] The corrected estimated temperature replaces the original estimated temperature The input energy-saving control module, and mark the current blind area j as "closed-loop correction state", and record the correction value and closed-loop identification source for subsequent trend analysis and model adjustment;

[0213] In this embodiment, the default initial value of β is set to 0.7, and when all boundary standard area temperature rise heights are consistent, that is, the standard deviation is less than 0.2℃, β is adjusted to 0.9;

[0214] If the subsequent boundary closed-loop structure is disintegrated (for example, the temperature of a certain standard area drops below the threshold value), the correction state is removed and the original estimated temperature is restored.

[0215] Embodiment 3

[0216] The energy-saving monitoring system for the assembled refrigeration machine room based on data analysis, characterized in that it comprises:

[0217] The interval module is used to divide the machine room space into multiple monitoring intervals and bind with the structure unit;

[0218] The excitation module is used to apply power disturbance to the structure unit to obtain structure excitation data;

[0219] The identification module is used to generate a thermal influence coefficient matrix according to the excitation data and the temperature change of the adjacent monitoring interval;

[0220] The calculation module is used to calculate the blind area temperature based on the thermal influence coefficient matrix, structure energy consumption data and adjacent interval temperature, and output the estimated temperature and covariance;

[0221] The processing module is used to judge the confidence of the estimated temperature, and trigger the update of the thermal influence coefficient matrix when the preset condition is not met;

[0222] The energy-saving control module is used to adjust the operating parameters of the refrigeration system according to the space temperature field and load prediction results, so as to achieve the energy-saving operation goal.

[0223] Compared with embodiment 2, in the case where the processing module does not form a closed loop outside the monitoring blind area, if it is identified that there are multiple similar temperature arc-shaped distribution structures in the standard area, the estimated temperature of the blind area is corrected according to the temperature difference between each distribution structure.

[0224] The method for the processing module to correct the estimated temperature comprises:

[0225] Y1, non-closed-loop structure determination;

[0226] The processing module first determines whether there are enough standard areas outside the current blind area, which have a significant temperature rise but do not form a closed surrounding structure. If there are at least two standard areas with temperature rise in different directions (for example, only on the east side and the south side), and there is a discontinuous boundary in space, it is determined that the current structure is not a closed loop condition;

[0227] Y2, heat diffusion structure identification;

[0228] The processing module further analyzes the spatial distribution of these temperature rise areas to determine whether they conform to the typical heat diffusion trend. If these standard areas are arranged in a certain arc, ellipse or fan shape in the plane or three-dimensional space, and their temperature values gradually decrease in the spatial direction, it indicates that the structure may be an open heat diffusion boundary;

[0229] Y3, similar temperature area screening;

[0230] The processing module screens standard monitoring areas with similar temperatures in the candidate arc-shaped area to form an arc-shaped distribution structure set, and the judgment basis includes:

[0231] y31, the temperature rise amount difference of multiple standard areas is less than a preset difference threshold;

[0232] y32, the spatial arrangement forms a visible arc line or a gradual curve;

[0233] y33, the distance between the areas and the temperature change trend meet the expected direction of heat diffusion (temperature gradually decreases with distance);

[0234] Y4, blind area estimated temperature correction;

[0235] The processing module combines the position relationship of the blind area relative to each arc-shaped structure, and the processing module corrects the current estimated temperature of the blind area according to the identified multiple arc-shaped temperature differences;

[0236] The correction direction is based on the trend of the arc-shaped temperature center, and the correction amplitude is determined according to the cumulative or weighted average value of the temperature difference distribution trend in each direction. The corrected temperature is used as the new estimated temperature for the energy-saving control module;

[0237] In this embodiment, the specific correction method includes:

[0238] The processing module first determines the three-dimensional coordinates of the current blind area in the overall machine room monitoring grid, and marks the arc-shaped temperature distribution structure adjacent to the blind area. In each arc-shaped structure, the "temperature center position" of the structure is defined as the standard area with the highest temperature in the structure;

[0239] The processing module calculates the spatial distance between the blind area center position and the temperature center of each arc-shaped structure, judges whether the blind area is inside, on the edge or outside the heat diffusion direction, so as to determine the directionality of temperature correction;

[0240] For each arc-shaped structure identified as valid, the representative temperature rise value, i.e. the temperature difference between the structure temperature center and the peripheral low-temperature boundary standard region, is extracted, and is recorded as the local temperature difference value of the structure;

[0241] If multiple arc-shaped structures are identified (such as the south side, southwest side, and southeast side), the temperature difference and the relative spatial angle of each direction are recorded respectively;

[0242] The processing module constructs a temperature difference weight distribution model according to the spatial direction, angle between the blind area and each arc-shaped structure, and distance. The temperature difference value of each direction will be calculated according to its spatial correlation with the blind area center to obtain the weight:

[0243] The direction with a shorter distance from the blind area has a higher weight;

[0244] The structure with a spatial angle aligned with the direction of the blind area center has a higher weight;

[0245] The direction with a more stable temperature difference change has a higher weight;

[0246] Finally, the weighted average value of the product of these direction weights and the corresponding temperature difference is calculated as the correction amplitude;

[0247] Y5, state output and marking;

[0248] Mark this round of correction as "non-closed loop heat diffusion correction state", and keep the temperature difference features used for estimation in the data record for subsequent trend learning and adaptive update of the estimation model.

[0249] The above formulas are dimensionless numerical calculations, and the formulas are obtained by software simulation of a large amount of data to obtain the most recent real situation. The preset parameters and threshold values in the formula are set by a person skilled in the art according to the actual situation.

[0250] The above is only a preferred embodiment of the present application, and is not intended to limit the present application in any form. Although the present application has been disclosed as above with a preferred embodiment, it is not intended to limit the present application. Any person skilled in the art can make some changes or modifications to the above disclosed technical content without departing from the scope of the technical solution of the present application, and any simple modification, equivalent change and modification of the above embodiments made according to the technical essence of the present application are still within the scope of the technical solution of the present application.

Claims

1. A data analysis-based energy-saving monitoring system for prefabricated refrigeration rooms, characterized in that: include: The interval module is used to divide the computer room space into multiple monitoring intervals and bind them to the structural units; The excitation module is used to apply power perturbations to the structural units and acquire structural excitation data; The identification module is used to generate a thermal influence coefficient matrix based on the excitation data and the temperature changes in adjacent monitoring intervals; The calculation module calculates the estimated temperature of the blind zone based on the heat transfer capacity of each structural unit to the adjacent monitoring interval in the thermal influence coefficient matrix, the current energy consumption input data of the structural unit, and the real-time temperature change of the adjacent monitoring interval, combined with the proportional extrapolation relationship. When the standard area adjacent to the blind zone is disturbed by the external environment, the calculation module determines whether to correct the estimated temperature of the current blind zone based on the temperature change sequence of the standard area, the change trend of the external environment, and the duration of the disturbance. The determination method of the calculation module includes the following steps: A1. Identify monitoring areas that are in direct contact with the boundaries of external structures as candidate interference-sensitive areas; A2. For the standard area adjacent to the blind zone, extract the temperature change sequence within the current estimation period and construct a temperature rise trend model; A3. Synchronously acquire environmental parameters for the corresponding time period and correlate them with temperature changes in the standard area; A4. If the temperature rise rate of the standard area per unit time is significantly higher than the historical steady-state average, and there is no corresponding structural power output fluctuation, then mark the standard area as a "potentially affected by external interference area" and record the duration of the interference. The processing module is used to determine the confidence level of the estimated temperature and trigger the update of the thermal influence coefficient matrix when the preset conditions are not met. The energy-saving control module is used to adjust the operating parameters of the refrigeration system based on the spatial temperature field and load prediction results to achieve the goal of energy-saving operation.

2. The energy-saving monitoring system for prefabricated refrigeration room based on data analysis according to claim 1, characterized in that, The processing module then performs the following operations: B1. Obtain the standard area that has been marked as "potentially affected by external disturbances" and determine whether its adjacent blind area is the estimated blind area j. If so, mark the corresponding blind area as a candidate for correction. B2. Correction of conditional judgment: If the following two conditions are met: The standard area marked as "potentially subject to external disturbance" has a continuous temperature rise time that exceeds the preset temperature rise time threshold. Covariance of temperature estimated in current blind zone j Less than the upper confidence limit; Then proceed to the estimated temperature correction process; B3. Calculation of temperature rise in standard area: Through the formula: Calculate the temperature change in the standard area ; In the formula, This represents the real-time temperature value of the standard area at the current moment. This is the reference steady-state temperature value for the standard region; B4. Blind Zone Estimated Temperature Correction: For estimating temperature Adjust the offset to obtain the corrected estimated temperature. ; α is the disturbance correction coefficient.

3. The energy-saving monitoring system for prefabricated refrigeration room based on data analysis according to claim 1, characterized in that, When a closed-loop structure is formed by multiple standard areas with temperature rise exceeding the threshold outside the monitoring blind zone, the processing module calculates the average temperature rise of the closed-loop area and corrects the current estimated temperature of the blind zone based on the temperature rise.

4. The energy-saving monitoring system for prefabricated refrigeration room based on data analysis according to claim 3, characterized in that, The correction method includes the following steps: Z1. The processing module traverses the surrounding area of ​​each blind zone j based on the spatial topology and adjacency matrix of the monitoring interval. If the blind zone j is surrounded by multiple adjacent standard zones, and the temperature rise of the standard zones surrounding the blind zone j is greater than the preset temperature rise threshold, then the processing module determines that there is a closed high-temperature boundary structure outside the blind zone j. Z2. The processing module extracts the temperature rise of all standard regions forming a closed loop and calculates their average temperature rise. ; Z3. Using the formula: Estimate the temperature of the current blind spot. Perform an offset to obtain the estimated temperature after correcting for the current blind zone. ; In the formula, ∈ (0.5, 1.0), which is the closed-loop isothermal correction coefficient.

5. The energy-saving monitoring system for prefabricated refrigeration room based on data analysis according to claim 1, characterized in that, If the processing module identifies multiple arc-shaped distribution structures with similar temperatures in the standard area when a closed loop is not formed outside the monitoring blind zone, it corrects the estimated temperature of the blind zone based on the temperature difference between each distribution structure.

6. The energy-saving monitoring system for prefabricated refrigeration room based on data analysis according to claim 5, characterized in that, The method for correcting the estimated temperature by the processing module includes: Y1. The processing module first determines whether there are multiple standard monitoring areas distributed in different directions outside the blind zone, and then analyzes the temperature changes of these areas respectively. When two or more consecutive standard regions are identified in at least two spatial directions, and their temperatures show an upward trend exceeding the set temperature rise threshold within the current estimation period, and these standard regions cannot be spatially enclosed by a blind zone, the blind zone is considered to be under non-closed-loop structure conditions. Y2. The processing module further analyzes the spatial distribution of these temperature rise areas to determine whether they conform to the trend of heat diffusion. Y3. The processing module filters standard monitoring areas with similar temperatures within the candidate arc-shaped regions to form an arc-shaped distribution structure set. The judgment criteria include: y31. The temperature rise difference between multiple standard areas is less than the preset difference threshold; y32. Spatial arrangement forms visible arcs or gradient curves; y33, The trend of inter-regional distance and temperature change meets the expected direction of heat diffusion; Y4. The processing module combines the positional relationship of the blind zone relative to each arc structure, and determines the dominant direction of temperature change based on the temperature difference along the arc path in the identified multiple arc structures. Based on this, according to the relative geometric position of the blind zone in the arc structure, the average or weighted average of the temperature difference in multiple arc directions is used to make a directional correction to the current estimated temperature.

Images