A cooling tower regulation system based on Internet of Things interaction
Through the cooling tower regulation system based on IoT interaction, the cooling tower data is monitored and analyzed in real time, abnormalities are identified and parameters are adjusted, and the problems of data synchronization and response delay in the prior art are solved, improving the reliability and energy efficiency of the system.
Patent Information
- Application Number
- CN202411254285.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-09
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-09-09
Smart Images

Figure CN118761022B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of cooling tower regulation, and in particular to a cooling tower regulation system based on Internet of Things interaction. Background Art
[0002] The Cooling Tower Regulation Technology area involves the design, optimization, and operational management of cooling tower systems. Cooling towers are one of the core components used in industrial and large facilities to remove excess heat generated by the process. This technology area involves monitoring and controlling the water temperature, flow, and chemical composition in the cooling tower to optimize energy efficiency and water quality. It also involves the use of sensors and control systems to automatically adjust fan speeds, pump operation, and cooling water distribution to respond to different environmental and operating conditions. These technologies can significantly improve cooling efficiency and reduce energy consumption while extending the life of the equipment.
[0003] Among them, the cooling tower regulation system refers to the system used to regulate the internal conditions of the cooling tower to ensure the optimization of efficiency and performance. These systems enable the cooling tower to work effectively under various operating conditions by precisely controlling the flow, temperature and chemical treatment of cooling water. Its main purpose is to maintain the appropriate operating temperature of machinery and equipment in the industrial production process by controlling the heat dissipation process to avoid overheating that damages equipment or reduces efficiency. By achieving these functions, the cooling tower regulation system plays an important role in maintaining production safety, improving energy efficiency and reducing operation and maintenance costs.
[0004] Existing cooling tower regulation technology has deficiencies in continuous data monitoring and real-time performance, especially in data synchronization and real-time analysis capabilities. Data processing in existing systems often relies on preset periodic updates, which cannot effectively respond to sudden environmental changes or abnormal equipment performance, resulting in response delays and increased instability and risk in system operation. In addition, although traditional technologies cover basic monitoring and regulation, they have not been fully utilized in terms of in-depth data analysis and predictive maintenance, resulting in the failure to fully realize the performance optimization and fault prevention potential of cooling towers under complex operating conditions. These technical limitations make it difficult for traditional cooling tower systems to achieve optimal operating efficiency in dynamic and highly changing industrial environments, affecting production continuity and the long-term reliability of equipment. Summary of the invention
[0005] The purpose of the present invention is to solve the shortcomings existing in the prior art and to propose a cooling tower adjustment system based on Internet of Things interaction.
[0006] In order to achieve the above object, the present invention adopts the following technical solution: A cooling tower adjustment system based on Internet of Things interaction includes:
[0007] The data receiving module receives temperature and flow data from the Internet of Things, combines it with environmental humidity and temperature data, uses a timestamp to mark each incoming data, compares the time interval between incoming data, adjusts the data time interval to eliminate deviations, and obtains the incoming data sequence;
[0008] The real-time monitoring module monitors the operating status of the cooling tower based on the incoming data sequence, collects temperature and flow rate change data, compares the change of the current data point with the historical data pattern, collects and records the difference between the data points, and generates a monitoring log with time series marks;
[0009] The change point analysis module is based on the monitoring log with time series marks, and is used to display key changes in temperature or flow by identifying mutation points in the data, calculating the time point of occurrence for each mutation point, comparing the time point with the periodic change data, identifying potential operating anomalies, and generating change point event records;
[0010] The regulation strategy module adjusts the cooling water flow and fan speed parameters based on the change point event records, matches the current operating state with the preset response strategy, adjusts the operation response sensitivity, responds to changes in system demand, and records the cooling tower regulation output.
[0011] As a further solution of the present invention, the step of acquiring the incoming data sequence is specifically:
[0012] Receive temperature, flow, ambient humidity and air temperature data, add a timestamp to each data item, using the formula:
[0013] ,
[0014] Generates time-stamped data tuples ;
[0015] in, , , , Represent the weight coefficients of temperature, flow, humidity and air temperature data respectively, , , , Represent the temperature, flow rate, ambient humidity and air temperature of the i-th data point respectively, is the timestamp of the ith data point;
[0016] Based on the data tuple with time stamp, the formula is adopted:
[0017] ,
[0018] Calculate the time interval between data points, use absolute values to ensure non-negativity, and generate an array of time intervals ;
[0019] Normalize the time interval array using the formula:
[0020] ,
[0021] Ensure the ratio of time intervals and generate standardized time intervals ;
[0022] in, is the sum of all data point intervals;
[0023] The data sequence is reconstructed according to the standardized time interval, and the standardized time interval and the original data are combined to provide a data synthesis method through time-weighted averaging, using the formula:
[0024] ,
[0025] Generate an incoming data sequence S.
[0026] As a further solution of the present invention, the step of obtaining the monitoring log with time sequence mark is specifically:
[0027] Extract real-time temperature and flow data from the incoming data sequence using the formula:
[0028] ,
[0029] Get real-time data series;
[0030] in, Represents a real-time data sequence, and are the temperature and flow data extracted from S, , is the adjustment factor for temperature and flow data;
[0031] Compare the current real-time data series The real-time data sequence of the previous moment , calculate the change and assess the deviation from the historical pattern using the formula:
[0032] ,
[0033] Generate delta data ;
[0034] in, is the standard deviation, is the sensitivity coefficient;
[0035] According to the monitoring log of the change data record, a dynamic weighting method is applied to enhance the attention to recent changes, using the formula:
[0036] ,
[0037] Generate a monitoring log L with time series marking;
[0038] Where T is the total monitoring time, is the time decay constant.
[0039] As a further solution of the present invention, the step of obtaining the time point is specifically as follows:
[0040] Analyze the temperature or flow data from the monitoring log with time series marks to identify potential mutation points, using the formula:
[0041] ,
[0042] Calculate the normalized rate of change ;
[0043] in, A small positive number representing numerical stability;
[0044] The normalized change rate is compared with the set sensitivity threshold to determine the significant mutation point, using the formula:
[0045] ,
[0046] Generate mutation markers ;
[0047] in, represents the basic threshold, represents the sensitivity adjustment factor;
[0048] From the mutation markers, extract the time points where all the markers are true to form a set of time points for the mutation event, using the formula:
[0049] ,
[0050] Generation time point ;
[0051] in, represents the set of all time points marked as mutations, Indicates whether a mutation occurs at time point t.
[0052] As a further solution of the present invention, the step of obtaining the change point event record is specifically as follows:
[0053] The time point and periodic variation data are analyzed using the formula:
[0054] ,
[0055] The calculated value is the weighted standardized difference between the time point and the period data, generating the standardized difference data. ;
[0056] in, Represents periodic variation data, is the numerical stability parameter, is a smoothing parameter used to adjust the influence of the denominator;
[0057] The standardized difference data was analyzed by applying a threshold, using the formula:
[0058] ,
[0059] Used to adjust the sensitivity of the threshold and generate anomaly markers ;
[0060] in, is the base difference threshold, yes The standard deviation of is the threshold adjustment offset;
[0061] Integrate all the abnormal marks, and summarize each marked abnormal time point t into an event record, using the formula:
[0062] ,
[0063] Provide weighted records of abnormal time points and generate change point event records E;
[0064] in, is the weight at time point t.
[0065] As a further solution of the present invention, the step of recording the cooling tower adjustment output is specifically:
[0066] The impact data is obtained from the change point event record using the formula:
[0067] ,
[0068] Calculate and generate preliminary adjustment parameter F;
[0069] in, , , , is the adjustment coefficient, S represents the current water flow, V represents the fan speed, and C represents the environmental parameters. Used to ensure the stability of mathematical operations;
[0070] The preliminary adjustment parameters are matched with the preset operation status and response strategy, using the formula:
[0071] ,
[0072] Calculate and generate the adjusted operating parameter G;
[0073] in, is the normalization factor;
[0074] According to the adjusted operating parameters, adjust the cooling water flow and fan speed, monitor the system response and record the output results, using the formula:
[0075] ,
[0076] Generate cooling tower regulation output H;
[0077] in, is the accuracy coefficient of output regulation, is the baseline adjustment factor.
[0078] Compared with the prior art, the advantages and positive effects of the present invention are:
[0079] In the present invention, by real-time synchronization and analysis of comprehensive data related to the cooling tower, including ambient humidity and air temperature, the real-time processing of data and abnormal identification are optimized, and the ability to respond immediately to changes in the cooling system is improved. In particular, the data is synchronized through timestamp marking to ensure the accuracy of processing. By real-time recording of differences between data points and rapid identification of mutation points, the system can accurately diagnose and respond to potential operational anomalies, significantly improving the reliability of the system. Real-time adjustment of cooling water flow and fan speed reflects rapid adaptation to environmental changes, effectively reduces energy waste, and improves the overall economy and environmental friendliness of the system. BRIEF DESCRIPTION OF THE DRAWINGS
[0080] Figure 1 is a system flow chart of the present invention;
[0081] Figure 2 A flow chart of the steps for obtaining the incoming data sequence of the present invention;
[0082] Figure 3 A flow chart of the steps for obtaining a monitoring log with a time sequence mark according to the present invention;
[0083] Figure 4 A flow chart of the steps for obtaining the time point of the present invention;
[0084] Figure 5 A flowchart of the steps for obtaining a change point event record of the present invention;
[0085] Figure 6 A flow chart of the steps for recording the cooling tower regulation output of the present invention. DETAILED DESCRIPTION
[0086] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0087] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.
[0088] Embodiment 1:
[0089] See also Figure 1 , a cooling tower regulation system based on Internet of Things interaction includes:
[0090] The data receiving module receives temperature and flow data from the Internet of Things, combines it with environmental humidity and temperature data, uses a timestamp to mark each incoming data, compares the time interval between incoming data, adjusts the data time interval to eliminate deviations, and obtains the incoming data sequence;
[0091] The real-time monitoring module monitors the operating status of the cooling tower based on the incoming data sequence, collects temperature and flow rate change data, compares the change of the current data point with the historical data pattern, collects and records the difference between the data points, and generates a monitoring log with time series tags;
[0092] The change point analysis module is based on monitoring logs with time series marks. It identifies mutation points in the data to display key changes in temperature or flow. It calculates the time point of each mutation point, compares the time point with the periodic change data, identifies potential operational anomalies, and generates change point event records.
[0093] The regulation strategy module adjusts the cooling water flow and fan speed parameters based on the change point event records, matches the current operating state with the preset response strategy, adjusts the operation response sensitivity, responds to changes in system demand, and records the cooling tower regulation output;
[0094] The incoming data sequence includes timestamp, time interval, and data deviation calibration. The monitoring log includes time series mark, data point change, and difference record. The change point event record includes mutation point identification, key change display, and time point calculation. The cooling tower regulation output includes flow adjustment, fan speed parameters, and operation response sensitivity.
[0095] See also Figure 2 , the specific steps for obtaining the incoming data sequence are:
[0096] Receive temperature, flow, ambient humidity and air temperature data, add a timestamp to each data item, using the formula:
[0097] ,
[0098] Generates time-stamped data tuples ;
[0099] in, , , , Represent the weight coefficients of temperature, flow, humidity and air temperature data respectively, , , , Represent the temperature, flow rate, ambient humidity and air temperature of the i-th data point respectively, is the timestamp of the ith data point;
[0100] Based on the data tuples with time stamps, the formula is:
[0101] ,
[0102] Calculate the time interval between data points, use absolute values to ensure non-negativity, and generate an array of time intervals ;
[0103] Normalize the time interval array using the formula:
[0104] ,
[0105] Ensure the ratio of time intervals and generate standardized time intervals ;
[0106] in, is the sum of all data point intervals;
[0107] Reconstruct the data sequence according to the standardized time interval, combine the standardized time interval and the original data, and provide a data synthesis method through time-weighted averaging, using the formula:
[0108] ,
[0109] Generate an incoming data sequence S.
[0110] Step 1:
[0111] formula: ,
[0112] Parameter explanation and derivation:
[0113] , , , It is the adjustment coefficient, which is used to adjust the influence weight of multiple physical quantities (temperature, flow, humidity, air temperature) in the data tuple;
[0114] , , , Represent the temperature, flow rate, ambient humidity and air temperature of the i-th data point respectively;
[0115] is the timestamp of the ith data point.
[0116] Calculation process (assuming data):
[0117] Assume that a data point value is (temperature), (flow), (humidity), (Temperature).
[0118] The adjustment factor is assumed to be =0.5, =1.5, =1.0, =0.3;
[0119] Plugging the data into the formula, we get:
[0120] ,
[0121] final It represents the i-th data point at a given timestamp Weighted temperature and flow, humidity and air temperature under.
[0122] Step 2:
[0123] formula: ,
[0124] Parameter explanation and derivation:
[0125] , are the timestamps of two consecutive data points.
[0126] Calculation process (assuming data):
[0127] Assumptions and , time is measured in minutes.
[0128] Calculate the time interval:
[0129] ,
[0130] Step 3:
[0131] formula: ,
[0132] Parameter explanation and derivation:
[0133] is the time interval between the i-th to i+1-th data points; is the sum of all the data point intervals.
[0134] Calculation process (assuming data):
[0135] Assuming there are 12 data points in an hour, and each interval is 5 minutes, the total minute.
[0136] Calculated as .
[0137] Step 4:
[0138] formula: ,
[0139] Parameter explanation and derivation:
[0140] is a tuple of timestamp and data; is the normalized time interval.
[0141] Calculation process (assuming data):
[0142] Use the above and ;
[0143] S is calculated as .
[0144] The final result will give a weighted composite data series, representing the average characteristics of the data over the entire time period.
[0145] See also Figure 3 , the specific steps for obtaining monitoring logs with time series marks are:
[0146] Extract real-time temperature and flow data from the incoming data sequence using the formula:
[0147] ,
[0148] Get real-time data series;
[0149] in, Represents a real-time data sequence, and are the temperature and flow data extracted from S, , is the adjustment factor for temperature and flow data;
[0150] Compare current real-time data series Real-time data sequence with the previous moment , calculate the change and assess the deviation from the historical pattern using the formula:
[0151] ,
[0152] Generate delta data ;
[0153] in, is the standard deviation, is the sensitivity coefficient;
[0154] According to the monitoring log of the change data, the dynamic weighting method is applied to enhance the attention to the recent changes, using the formula:
[0155] ,
[0156] Generate a monitoring log L with time series marking;
[0157] Where T is the total monitoring time, is the time decay constant.
[0158] Detailed explanation of formula and calculation:
[0159] Step 1: Real-time data series Calculation:
[0160] ,
[0161] Parameter Description:
[0162] and is the weight coefficient of temperature and flow data, adjusting the output of each data source Contribution ratio;
[0163] and are the temperature and flow data at time t.
[0164] Calculation process and examples:
[0165] Assume that the temperature at time t is and flow .
[0166] Set the weight factor =0.7 and =0.3, and the coefficient is assumed to be set based on previous operating experience and data importance.
[0167] calculate : ,
[0168] Analysis of calculation results: The real-time data index obtained after considering the influence of temperature and flow is 57. The index can be used to analyze or monitor the decision-making process of the system.
[0169] Step 2: Change data Calculation:
[0170] formula: ,
[0171] Parameter Description:
[0172] , They are the real-time data sequence values of the current and previous moments respectively; is the standard deviation of historical data, used to standardize the variation; is the sensitivity factor, which is used to enhance the response to significant changes.
[0173] Calculation process and examples:
[0174] Assumptions ,current Calculated as in step 1.
[0175] Standard deviation of historical data , sensitivity coefficient .
[0176] calculate :
[0177] ,
[0178] Analysis of calculation results: It means that the standardized change index between the current and previous data is 1.05, which is used to analyze the fluctuation degree and trend of data.
[0179] Step 3: Calculation of monitoring log L
[0180] formula: ,
[0181] Parameter Description:
[0182] T is the total monitoring time; is the time decay constant, adjusting the weight of early data points.
[0183] Calculated as in step 2.
[0184] Calculation process and examples:
[0185] Assuming the total monitoring time T = 10 days, the time decay constant .
[0186] Use the Value, calculate the accumulation of L:
[0187] ,
[0188] Simplified to daily Similarly, the actual situation requires daily actual .
[0189] The cumulative calculation is done using programming software or manual calculation, the number depends on the daily and the calculated value of e.
[0190] Analysis of calculation results:
[0191] L represents the change in the entire monitoring period after reference to the time decay effect, which can be used to evaluate the stability or abnormal activity of the system during the entire period.
[0192] See also Figure 4 , the specific steps for obtaining the time point are:
[0193] Analyze temperature or flow data from monitoring logs with time series tags to identify potential mutation points using the formula:
[0194] ,
[0195] Calculate the normalized rate of change ;
[0196] in, A small positive number representing numerical stability;
[0197] Compare the normalized change rate with the set sensitivity threshold to determine the significant mutation point using the formula:
[0198] ,
[0199] Generate mutation markers ;
[0200] in, represents the basic threshold, represents the sensitivity adjustment factor;
[0201] Extract all the time points where the marks are true from the mutation marks to form the time point set of the mutation event, using the formula:
[0202] ,
[0203] Generation time point ;
[0204] in, represents the set of all time points marked as mutations, Indicates whether a mutation occurs at time point t.
[0205] Detailed explanation and derivation of the formula for step 1:
[0206] formula: ,
[0207] : Data record at time point t; : Data record at time point t-1; : A small positive number to avoid division by zero errors; : Normalized rate of change at time point t.
[0208] Derivation process:
[0209] Assume that the temperature data at time points t and t-1 are 300K and 295K respectively, select To avoid division by zero errors.
[0210] Compute the square of the difference:
[0211] ,
[0212] Calculate the normalized denominator:
[0213] ,
[0214] Calculate the normalized rate of change :
[0215] ,
[0216] Numerical meaning:
[0217] Normalized rate of change It represents the relative proportion of temperature change from time point t-1 to t, which is very small here, indicating that the change is very small.
[0218] Detailed explanation and derivation of the formula for step 2:
[0219] formula: ,
[0220] : The basic threshold is assumed to be 0.002, which is a threshold for judging mutations set based on experience;
[0221] : Sensitivity adjustment coefficient, assumed to be 1.5, used to adjust the sensitivity of the threshold according to actual conditions;
[0222] : Boolean value, indicating whether the time point t is a mutation point.
[0223] Derivation process:
[0224] Calculate the adjusted threshold: ,
[0225] Determine mutation: ,
[0226] Numerical meaning: Indicates that no significant mutation occurred at time point t.
[0227] Detailed explanation and derivation of the formula for step 3:
[0228] formula: ,
[0229] : The set of all time points marked as mutations.
[0230] Derivation process:
[0231] Since in the previous step is False, so The current time point t will not be included.
[0232] Numerical meaning:
[0233] The empty set means that no significant mutations were detected under the given data and threshold settings.
[0234] See also Figure 5 , the specific steps for obtaining the change point event record are:
[0235] Analyze the time point and period change data, using the formula:
[0236] ,
[0237] The calculated value is the weighted standardized difference between the time point and the period data, generating the standardized difference data. ;
[0238] in, Represents periodic variation data, is the numerical stability parameter, is a smoothing parameter used to adjust the influence of the denominator;
[0239] A threshold was applied to the normalized difference data for analysis using the formula:
[0240] ,
[0241] Used to adjust the sensitivity of the threshold and generate anomaly markers ;
[0242] in, is the base difference threshold, yes The standard deviation of is the threshold adjustment offset;
[0243] Integrate all abnormal marks and summarize each marked abnormal time point t as an event record using the formula:
[0244] ,
[0245] Provide weighted records of abnormal time points and generate change point event records E;
[0246] in, is the weight at time point t.
[0247] Formula and analysis for step 1:
[0248] formula: ,
[0249] Assumptions:
[0250] Assuming periodic variation data At a certain moment, the value of t is 150;
[0251] Assumed mutation time point is 140;
[0252] set up is 1, which is a small positive number used to ensure that the denominator is non-zero;
[0253] set up is 10, which is the parameter used to smooth the denominator.
[0254] Calculation process:
[0255] calculate and The square of the difference: ,
[0256] Calculate the maximum value function ,if The maximum value of is 200, then .
[0257] Will Add to Take the square root, add : ,
[0258] calculate : ;
[0259] Result analysis: The value is 4.142, which means that at time point t, the normalized time difference value is 4.142, indicating the standard deviation relative to the maximum cycle value.
[0260] Formula and analysis for step 2:
[0261] formula: ,
[0262] Assume data:
[0263] Use the result from step 1 Value 4.142; assumed threshold is 0.5; assuming periodic data Standard Deviation is 30; assuming is 2.
[0264] Calculation process:
[0265] Calculate the threshold product: ,
[0266] Compare Multiply by the threshold: (This comparison result is false, indicating no abnormality)
[0267] Result analysis:
[0268] A result of False indicates that no significant abnormality was detected at time point t.
[0269] Formula and analysis for step 3:
[0270] formula: ,
[0271] Assume data:
[0272] Assume that time point t=10 and is true (this is a hypothetical situation, the actual result of step 2 is false).
[0273] Assumption Weight is 1.5.
[0274] Calculation process:
[0275] Calculate the product of time point and weight: .
[0276] Result interpretation: The value of E is 15, which means that there is an abnormal event at time point t=10, and its importance score after weight adjustment is 15.
[0277] See also Figure 6 , the steps to record the cooling tower regulation output are as follows:
[0278] Obtain impact data from change point event records using the formula:
[0279] ,
[0280] Calculate and generate preliminary adjustment parameter F;
[0281] in, , , , is the adjustment coefficient, S represents the current water flow, V represents the fan speed, and C represents the environmental parameters. Used to ensure the stability of mathematical operations;
[0282] Match the preliminary adjustment parameters with the preset operating status and response strategy using the formula:
[0283] ,
[0284] Calculate and generate the adjusted operating parameter G;
[0285] in, is the normalization factor;
[0286] According to the adjusted operating parameters, adjust the cooling water flow and fan speed, monitor the system response and record the output results, using the formula:
[0287] ,
[0288] Generate cooling tower regulation output H;
[0289] in, is the accuracy coefficient of output regulation, is the baseline adjustment factor.
[0290] Step 1: Calculation of preliminary adjustment parameter F:
[0291] formula: ,
[0292] Variable resolution:
[0293] E: data recorded by the change point event, for example, E=5 (unit: number of events);
[0294] S: The water flow rate of the current system, set to S=200 liters / minute;
[0295] V: fan speed, set to V=1200 rpm;
[0296] C: Environmental parameters, such as the current temperature, set to C = 25 degrees Celsius;
[0297] : A small constant used to ensure the stability of logarithmic operations, set to =0.1;
[0298] , , , : Adjustment coefficient, assumed to be , , , ;
[0299] Calculation process:
[0300] calculate : ,
[0301] Calculate F: ,
[0302] Result analysis: F=19.44 is a parameter used for system adjustment calculations.
[0303] Step 2: Calculation of the adjusted operating parameter G
[0304] formula: ,
[0305] Variable resolution:
[0306] : Normalization factor, assumed to be ;
[0307] Calculation process:
[0308] Assumptions (Set a theoretical maximum value as the approximate value of the current F),
[0309] Calculate G:
[0310] ,
[0311] Result analysis: Indicates the adjusted operating parameter, the value will be used for system regulation.
[0312] Step 3: Calculation of cooling tower regulation output H:
[0313] formula: ,
[0314] Variable resolution:
[0315] : The accuracy coefficient of output regulation, assumed to be ; : Baseline adjustment factor, assumed to be ;
[0316] Calculation process:
[0317] Calculate H:
[0318] ,
[0319] Result interpretation: H = 2.0001 represents the output result of the cooling tower adjustment. The value includes the actual output after adjustment and the baseline adjustment of the system. The value indicates that the system has been adjusted to the nearly optimal state according to the calculation results.
[0320] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.
Claims
1. A cooling tower adjustment system based on Internet of Things interaction, It is characterized in that The system comprises: The data receiving module receives temperature and flow data from the Internet of Things, combines it with environmental humidity and temperature data, uses a timestamp to mark each incoming data, compares the time interval between incoming data, adjusts the data time interval to eliminate deviations, and obtains the incoming data sequence; The real-time monitoring module monitors the operating status of the cooling tower based on the incoming data sequence, collects temperature and flow rate change data, compares the change of the current data point with the historical data pattern, collects and records the difference between the data points, and generates a monitoring log with time series marks; The change point analysis module is based on the monitoring log with time series marks, and is used to display key changes in temperature or flow by identifying mutation points in the data, calculating the time point of occurrence for each mutation point, comparing the time point with the periodic change data, identifying potential operating anomalies, and generating change point event records; The steps for obtaining the change point event record are specifically as follows: The time point and periodic variation data are analyzed using the formula: , The calculated value is the weighted standardized difference between the time point and the period data, generating the standardized difference data. ; in, Represents periodic variation data, is the numerical stability parameter, is a smoothing parameter used to adjust the influence of the denominator, represents the set of all time points marked as mutations; The standardized difference data was analyzed by applying a threshold, using the formula: , Used to adjust the sensitivity of the threshold and generate anomaly markers ; in, is the base difference threshold, yes The standard deviation of is the threshold adjustment offset; Integrate all the abnormal marks, and summarize each marked abnormal time point t into an event record, using the formula: , Provide weighted records of abnormal time points and generate change point event records E; in, is the weight at time point t; The adjustment strategy module adjusts the cooling water flow and fan speed parameters based on the change point event record, matches the current operating state with the preset response strategy, adjusts the operation response sensitivity, responds to changes in system demand, and records the cooling tower adjustment output; The steps of recording the cooling tower adjustment output are specifically as follows: The impact data is obtained from the change point event record using the formula: , Calculate and generate preliminary adjustment parameter F; in, , , , is the adjustment coefficient, S represents the current water flow, V represents the fan speed, and C represents the environmental parameters. Used to ensure the stability of mathematical operations; The preliminary adjustment parameters are matched with the preset operation status and response strategy, using the formula: , Calculate and generate the adjusted operating parameter G; in, is the normalization factor; According to the adjusted operating parameters, adjust the cooling water flow and fan speed, monitor the system response and record the output results, using the formula: , Generate cooling tower regulation output H; in, is the accuracy coefficient of output regulation, is the baseline adjustment factor.
2. According to claim 1, the cooling tower adjustment system based on Internet of Things interaction, It is characterized in that The steps for acquiring the incoming data sequence are specifically as follows: Receive temperature, flow, ambient humidity and air temperature data, add a timestamp to each data item, using the formula: , Generates time-stamped data tuples ; in, , , , Represent the weight coefficients of temperature, flow, humidity and air temperature data respectively, , , , Represent the temperature, flow rate, ambient humidity and air temperature of the i-th data point respectively, is the timestamp of the ith data point; Based on the data tuple with time stamp, the formula is adopted: , Calculate the time interval between data points, use absolute values to ensure non-negativity, and generate an array of time intervals ; Normalize the time interval array using the formula: , Ensure the ratio of time intervals and generate standardized time intervals ; in, is the sum of all data point intervals; The data sequence is reconstructed according to the standardized time interval, and the standardized time interval and the original data are combined to provide a data synthesis method through time-weighted averaging, using the formula: , Generate an incoming data sequence S.
3. The cooling tower adjustment system based on Internet of Things interaction according to claim 2, It is characterized in that The steps for obtaining the monitoring log with time series mark are specifically as follows: Extract real-time temperature and flow data from the incoming data sequence using the formula: , Get real-time data series; in, Represents a real-time data sequence, and are the temperature and flow data extracted from S, , is the adjustment factor for temperature and flow data; Compare the current real-time data series The real-time data sequence of the previous moment , calculate the change and assess the deviation from the historical pattern using the formula: , Generate delta data ; in, is the standard deviation, is the sensitivity coefficient; According to the monitoring log of the change data record, a dynamic weighting method is applied to enhance the attention to recent changes, using the formula: , Generate a monitoring log L with time series marking; Where T is the total monitoring time, is the time decay constant.
4. The cooling tower adjustment system based on Internet of Things interaction according to claim 3, It is characterized in that The steps for obtaining the time point are specifically as follows: Analyze the temperature or flow data from the monitoring log with time series marks to identify potential mutation points, using the formula: , Calculate the normalized rate of change ; in, A small positive number representing numerical stability; The normalized change rate is compared with the set sensitivity threshold to determine the significant mutation point, using the formula: , Generate mutation markers ; in, represents the basic threshold, represents the sensitivity adjustment factor; From the mutation markers, extract the time points where all the markers are true to form a set of time points for the mutation event, using the formula: , in, represents the set of all time points marked as mutations, Indicates whether a mutation occurs at time point t.
Citation Information
Patent Citations
Central air-conditioning cooling water system energy efficiency monitoring system based on Internet of Things technology
CN106931603A
Decarburization electric control real-time data analysis system
CN118504930A
