WO2021161957A1

WO2021161957A1 - Energy management device, server, energy management system, energy management method, and energy management program

Info

Publication number: WO2021161957A1
Application number: PCT/JP2021/004578
Authority: WO
Inventors: 直聡坂本; 裕樹松本; 勇林
Original assignee: 三菱電機株式会社
Priority date: 2020-02-10
Filing date: 2021-02-08
Publication date: 2021-08-19
Also published as: JP7270827B2; TW202131267A; JPWO2021161957A1; CN115053252A; TWI762104B; WO2021161399A1

Abstract

An energy management device (10) is provided with an index value calculating unit (23), a score calculating unit (24), and an information providing unit (25). The index value calculating unit (23) calculates one or more types of index value relating to energy consumption by a diagnosis target, including a production facility, on the basis of production related information, which is information relating to historical production. On the basis of the one or more types of index value calculated by the index value calculating unit (23), the score calculating unit (24) calculates a score indicating a degree of influence on energy consumption that did not contribute to production, for each of a plurality of factor candidates, which are candidates of energy consumption factors that did not contribute to production. The information providing unit (25) outputs information relating to the factor candidates having at least the two highest scores calculated by the score calculating unit (24), among the plurality of factor candidates.

Description

Energy management equipment, servers, energy management systems, energy management methods, and energy management programs

This disclosure relates to an energy management device, a server, an energy management system, an energy management method, and an energy management program for diagnosing factors of energy consumption that did not contribute to production in a diagnosis target including production equipment.

Conventionally, there is known a technique of identifying factors of energy consumption that did not contribute to production in production equipment and presenting information on the identified factors to the user. For example, in Patent Document 1, information on factors of wasteful energy consumption when a characteristic pattern that occurs when wasteful energy consumption occurs appears in graph data showing the relationship between integrated production amount and integrated energy consumption amount. A technique for outputting a message including the above is disclosed.

Japanese Unexamined Patent Publication No. 2016-18242

However, the technique described in Patent Document 1 contributes to production when there are a plurality of energy consumption factors that did not contribute to production because the energy consumption factor that did not contribute to production is narrowed down to one. It can be difficult to take appropriate measures against energy consumption.

The present disclosure has been made in view of the above, and an object of the present disclosure is to obtain an energy management device capable of identifying a plurality of factors that have caused energy consumption that does not contribute to production.

In order to solve the above-mentioned problems and achieve the object, the energy management device of the present disclosure includes an index value calculation unit, a score calculation unit, and an information provision unit. The index value calculation unit calculates one or more types of index values related to energy consumption in the diagnosis target including the production equipment based on the production-related information which is the information related to the past production. The score calculation unit did not contribute to the production of each of the plurality of factor candidates, which are candidates for energy consumption factors that did not contribute to production, based on one or more types of index values calculated by the index value calculation unit. Calculate a score that indicates the degree of impact on energy consumption. The information providing unit outputs information on two or more factor candidates having the highest score calculated by the score calculation unit among the plurality of factor candidates.

According to the present disclosure, it is possible to identify a plurality of factors that have caused energy consumption that does not contribute to production.

The figure which shows an example of the structure of the production facility including the energy management apparatus which concerns on Embodiment 1. The figure which shows an example of the structure of the energy management apparatus which concerns on Embodiment 1. The figure which shows an example of the 1st factor candidate information generated by the information generation part of the energy management apparatus which concerns on Embodiment 1. The figure which shows an example of the 2nd factor candidate information determined by the information generation part which concerns on Embodiment 1. The figure for demonstrating the 1st index, the 2nd index, the 3rd index, the 4th index, and the 5th index which the value is calculated by the index value calculation part which concerns on Embodiment 1. The figure which shows an example of a plurality of kinds of index values calculated by the index value calculation unit which concerns on Embodiment 1. The figure which shows an example of the integrated information which concerns on Embodiment 1. The figure which shows an example of the loss factor information displayed on the display part by the information providing part which concerns on Embodiment 1. A flowchart showing an example of processing by the processing unit of the energy management device according to the first embodiment. The figure which shows an example of the hardware composition of the processing part of the energy management apparatus which concerns on Embodiment 1. The figure which shows an example of the structure of the energy management apparatus which concerns on Embodiment 2. The figure which shows an example of the loss factor information displayed on the display part by the information providing part which concerns on Embodiment 2. A flowchart showing an example of processing by the processing unit of the energy management device according to the second embodiment. A flowchart showing an example of diagnostic processing by the processing unit of the energy management device according to the second embodiment. The figure which shows an example of the structure of the energy management system which concerns on Embodiment 3. The figure which shows an example of the structure of the energy management apparatus which concerns on Embodiment 3. The figure which shows an example of the configuration of the server which concerns on Embodiment 3. The figure which shows an example of the neural network which concerns on Embodiment 3. A flowchart showing an example of processing by the processing unit of the energy management device according to the third embodiment. A flowchart showing an example of learning processing by the server according to the third embodiment. A flowchart showing an example of inference processing by the server according to the third embodiment. A flowchart showing an example of processing by the mobile terminal according to the third embodiment. The figure which shows an example of the hardware configuration of the server which concerns on Embodiment 3. The figure which shows an example of the structure of the energy management system which concerns on Embodiment 4. The figure which shows an example of the configuration of the server which concerns on Embodiment 4. The figure which shows an example of the radar chart displayed on the display part of the mobile terminal which concerns on Embodiment 4. The figure which shows another example of the radar chart displayed on the display part of the mobile terminal which concerns on Embodiment 4. A flowchart showing an example of learning processing by the server according to the fourth embodiment. A flowchart showing an example of inference processing by the server according to the fourth embodiment.

The energy management device, server, energy management system, energy management method, and energy management program according to the embodiment will be described in detail below based on the drawings. It should be noted that this embodiment does not limit this disclosure.

Embodiment 1.
FIG. 1 is a diagram showing an example of the configuration of a production facility including the energy management device according to the first embodiment. As shown in FIG. 1, the production facility 1 according to the first embodiment includes a production facility 2, a related facility 3,

power sensors

4 and 5, a production volume sensor 6, an environment sensor 7, and a production control device 8. And an energy management device 10. In the following, the energy used by the production equipment 2 and the related equipment 3 is electric power, but may be primary energy such as petroleum, coal, gas, hydrogen, etc., and is a combination of electric power and primary energy. There may be.

Production equipment 2 executes a production process for producing a plurality of articles. In the production facility 2, for example, a production line is composed of a plurality of production devices, but the production facility 2 may have a configuration having only one production device. The article produced by the production facility 2 is, for example, an industrial product or a work-in-process product of an industrial product, and may be hereinafter referred to as a production target product. The product to be produced may be a liquid or a gas.

Related equipment 3 is equipment used in connection with production equipment 2. For example, the related equipment 3 is equipment such as a lighting device, an air conditioner, a compressor, or a dust collector that is turned on by an operator or the like when the product to be produced is produced by the production equipment 2. The related equipment 3 is also called a utility equipment.

The power sensor 4 is attached to a power transmission line that transmits power to the production equipment 2, the production equipment 2, or the like, periodically measures the power consumption of the production equipment 2, and provides information indicating the measured power consumption as an energy management device. Transmission to 10 via a dedicated line (not shown) or a network (not shown).

The power sensor 5 is attached to a power transmission line that transmits power to the related equipment 3, the related equipment 3, or the like, periodically measures the power consumption of the related equipment 3, and provides information indicating the measured power consumption as an energy management device. Transmission to 10 via a dedicated line (not shown) or a network (not shown). The power consumption measured by the power sensor 4 is an example of the energy consumption of the production equipment 2. The power consumption measured by the power sensor 5 is an example of the energy consumption of the related equipment 3.

The production amount sensor 6 is provided in the production equipment 2, periodically measures the production amount of the production equipment 2, and sends information indicating the measured production amount to the energy management device 10 by a dedicated line (not shown) or a network (not shown). Send via. The production amount sensor 6 counts, for example, the number of passing products to be produced in the production line of the production facility 2, and measures the counted value as the production amount. The production amount measured by the production amount sensor 6 is the production flow rate when the product to be produced is a liquid or a gas. Further, the production amount measured by the production amount sensor 6 may be expressed by weight or length.

The environment sensor 7 periodically measures the production environment, which is the environment in the production process of the production equipment 2, and transmits information indicating the measured production environment to the energy management device 10. The production environment measured by the environment sensor 7 is, for example, the temperature, humidity, carbon dioxide concentration, brightness, noise, vibration, or the like in the room where the production equipment 2 is arranged. The information indicating the production environment may be information input to a terminal device (not shown). In this case, the information indicating the production environment is transmitted from the terminal device (not shown) to the energy management device 10 via a dedicated line (not shown) or a network (not shown).

The production control device 8 has a storage unit (not shown) that stores production control information. The production control information includes daily information such as the type of the production target product, the person in charge of the production process, the error information of the production equipment 2, the number of lots of the production target product, and the takt time of the production equipment 2. The takt time is, for example, the time obtained by dividing the operating time of the production facility 2 in one day by the daily production amount.

The processing unit (not shown) in the production control device 8 reads the production control information stored in the storage unit from the storage unit, and reads the read information to the energy management device 10 via a dedicated line (not shown) or a network (not shown). Send. The production control device 8 can acquire a part of the production control information from the production facility 2 via a dedicated line (not shown) or a network (not shown).

Further, the production control device 8 can specify a part of the production control information by the image sensor. Further, the production control device 8 can also store the information input from the input unit (not shown) as a part of the production control information. The input unit can receive the input by the keyboard or the input by the voice recognition and output the received information to the production control device 8.

The energy management device 10 collects information from each of the

power sensors

4 and 5, the production volume sensor 6, the environment sensor 7, and the production control device 8, and based on the collected information, the production equipment 2 and the related equipment 3 are combined. Diagnose the factors of energy consumption that did not contribute to production in the diagnostic target including. In the following, energy consumption that does not contribute to production in the diagnosis target may be described as energy consumption or energy loss that does not contribute to production. The energy consumption that did not contribute to production includes, for example, the energy consumption of warm air required for the operation of the production equipment 2 (energy consumption of the production equipment 2 at the time T1 described later), and is indirectly used for production. In some cases, it can be regarded as contributing, but it also refers to energy consumption that we want to reduce as much as possible, as is the case with energy loss.

FIG. 2 is a diagram showing an example of the configuration of the energy management device according to the first embodiment. As shown in FIG. 2, the energy management device 10 includes a processing unit 11, a production-related information storage unit 12, and a display unit 13. The processing unit 11 includes an information collecting unit 21, an information generating unit 22, an index value calculating unit 23, a score calculating unit 24, and an information providing unit 25.

The information collecting unit 21 collects information from each of the

power sensors

4 and 5, the production amount sensor 6, the environment sensor 7, and the production management device 8, associates the collected information with the time of collection, and stores the production-related information. Add to 12 production-related information. The time of collection includes, for example, hour, minute, and second information, as well as year, month, and day information. The production-related information is information related to past production, and is information collected by the information collecting unit 21 and stored in the production-related information storage unit 12.

The information collected by the information collecting unit 21 may be either information indicated by an analog signal or information indicated by a digital signal. When the collected information is an analog signal, the information collecting unit 21 converts the information collected by AD (Analog to Digital) conversion into a digital signal. The information collecting unit 21 can also perform effective value calculation or filter processing on the collected information, for example.

The information generation unit 22 generates factor candidate information including a plurality of factor candidate information that is a candidate for a factor that causes energy loss, based on the production-related information stored in the production-related information storage unit 12. The factor candidate information includes the first factor candidate information and the second factor candidate information.

The information generation unit 22 generates the first factor candidate information based on the calendar information held internally and the production-related information stored in the production-related information storage unit 12. FIG. 3 is a diagram showing an example of first factor candidate information generated by the information generation unit of the energy management device according to the first embodiment.

As shown in FIG. 3, the first factor candidate information includes "month", "day of the week", "week", "production start time", and "production end time" for each "day", and "day". , "Month", "day of the week", "week", "production start time", and "production end time" are associated with each other.

"Day" is information indicating the date, "month" is information indicating the month, "day of the week" is information indicating the day of the week, and "week" is what "day" is "month". Information indicating whether it is the week. The "production start time" is information indicating the time when the production of the product to be produced by the production equipment 2 is started. The "production end time" is information indicating the time when the production of the product to be produced by the production equipment 2 is completed. In the example shown in FIG. 3, it is shown that "October 20, 2019" is the fourth Sunday of October, the production start time is 7:00, and the production end time is 17:00.

The information generation unit 22 acquires the "month" for each "day" from the information of the month included in the "day". Further, the information generation unit 22 determines the "day of the week" and the "week" for each "day" based on the calendar information held internally, and the determined "day of the week" and the "week" are the first factors. Include in candidate information. Further, the information generation unit 22 determines the daily "production start time" and "production end time" from the production-related information stored in the production-related information storage unit 12, and determines the "production start time" and "production". "End time" is included in the first factor candidate information.

The information generation unit 22 determines, for example, a time obtained by subtracting the time required to produce one production target product from the time when the power consumption of the production equipment 2 becomes equal to or higher than the preset threshold value Pth as the production start time. do. Further, the information generation unit 22 determines, for example, the time when the production amount of the production equipment 2 becomes less than the preset threshold value Mth as the production end time. When the production start time and the production end time are included in the production-related information, the information generation unit 22 can also specify the "production start time" and the "production end time" from the production-related information.

Further, the first factor candidate information may include, for example, information on the production amount on the current day and information on the production amount on the previous day. In this case, the information generation unit 22 calculates the total production amount on the current day as the production amount on the current day, and calculates the total production amount on the previous day as the production amount on the previous day. For example, the information on the production volume of the day on "October 20, 2019" is the total production volume on "October 20, 2019", and the information on the production volume on the previous day on "October 20, 2019" is. , The total production volume as of "October 19, 2019".

Further, the information generation unit 22 generates the second factor candidate information from the production-related information stored in the production-related information storage unit 12. The second factor candidate information is, for example, a daily representative value for each of the target model, the person in charge, and the occurrence error, assuming that each of the target model, the person in charge, and the occurrence error is expressed numerically. .. For example, the information generation unit 22 targets the mode of each of the target model, the person in charge, and the occurrence error in the daily time-series information included in the production-related information stored in the production-related information storage unit 12. Judge as a representative value of the model, the person in charge, and the error that occurred. The target model indicates the type of the target product, the person in charge indicates the person in charge of production in the production equipment 2, and the occurrence error indicates the type of the error generated in the production equipment 2.

FIG. 4 is a diagram showing an example of the second factor candidate information determined by the information generation unit according to the first embodiment. The second factor candidate information shown in FIG. 4 includes "target model", "person in charge", and "occurrence error" for each "day", and includes "target model", "person in charge", and "occurrence error". Are associated with each other.

In FIG. 4, an example in which the target model is at least "A1" or "A2", the person in charge is at least "B1" or "B2", and the occurrence error is at least "# 1" or "# 2". Is shown. In the example shown in FIG. 4, on October 20, 2019, "A1" was mainly produced as the target model, the person in charge "B2" was mainly in charge of production, and the most common error was "# 2". It is shown that there is.

The second factor candidate information is, for example, information indicating the average value and fluctuation range of each of the temperature, humidity, brightness, noise, and vibration in the room in which the production equipment 2 or the related equipment 3 is operating. including. For example, the information generation unit 22 averages and fluctuates each of the indoor temperature, humidity, brightness, noise, and vibration based on the environmental information included in the production-related information stored in the production-related information storage unit 12. Calculate the width and so on.

The index value calculation unit 23 calculates the value of one or more types of indexes related to energy consumption in the diagnosis target including the production equipment 2 and the related equipment 3 based on the information stored by the production-related information storage unit 12. In the following, the index value calculation unit 23 calculates the values of five types of indexes, but the types of indexes whose values are calculated by the index value calculation unit 23 may be four or less, and six or more. It may be.

The index value calculation unit 23 of the first index, the second index, the third index, the fourth index, and the fifth index based on the production-related information stored in the production-related information storage unit 12. Calculate each value. FIG. 5 is for explaining a first index, a second index, a third index, a fourth index, and a fifth index whose values are calculated by the index value calculation unit according to the first embodiment. It is a figure. In the following, the value of the first index calculated by the index value calculation unit 23 is described as the first index value, and the value of the second index calculated by the index value calculation unit 23 is referred to as the second index value. The value of the third index calculated by the index value calculation unit 23 is described as the third index value. Further, the value of the fourth index calculated by the index value calculation unit 23 is described as the fourth index value, and the value of the fifth index calculated by the index value calculation unit 23 is described as the fifth index value. do.

The first index value is the time T1 from when the production equipment 2 is turned on until the production of the production equipment 2 is started. In the index value calculation unit 23, for example, the difference between the time when the power consumption of the production equipment 2 becomes equal to or higher than the preset threshold Pth and the time when the production amount of the production equipment 2 becomes equal to or higher than the preset threshold Mth. Is calculated. The index value calculation unit 23 can calculate as the first index value the time obtained by subtracting the time required to produce one production target product in the production equipment 2 from the calculated difference. The first index can be said to be wasted time from the start of the production facility 2 to the start of production, and can be said to be the time during which energy consumption that does not contribute to production occurs.

The second index value is the time T2 from the end of production of production equipment 2 to the time when production equipment 2 is turned off. In the index value calculation unit 23, for example, the difference between the time when the production amount of the production equipment 2 becomes less than the preset threshold value Mth and the time when the power consumption amount of the production equipment 2 becomes less than the preset threshold value Pth. Can be calculated as the second index value. Such a second index can be said to be a wasted time from the end of production to the shutdown of the production equipment 2, and can be said to be the time during which energy consumption that does not contribute to production occurs.

The third index value is the time T3 indicating the difference between the time T4 when the related equipment 3 is on and the time T5 when the production equipment 2 is on. Such a third index indicates the time when the related equipment 3 is started while the production equipment 2 is stopped, and can be said to represent a wasted time, and can be said to be a time when energy consumption that does not contribute to production occurs.

The fourth index value indicates the ratio of the time during which production by production equipment 2 is performed to the time during which production equipment 2 is on. The index value calculation unit 23 determines, for example, the ratio of the time T6 in which the production amount of the production equipment 2 is equal to or greater than the preset threshold value Mth to the time T5 in which the power consumption of the production equipment 2 is equal to or greater than the preset threshold value Pth. be. It can be said that the smaller the fourth index value is, the longer the production is wasted during the time when the production equipment 2 is started. The more time that is wasted, the more energy consumption that does not contribute to production.

The fifth index value indicates the amount of power consumption per unit production output. The power consumption per unit production amount is obtained, for example, by dividing the daily power consumption amount by the daily production amount. Output is any unit, such as the number, weight, or length of the product to be produced.

The index value calculation unit 23 includes the production amount information included in the production-related information stored in the production-related information storage unit 12 and the production equipment 2 and related equipment included in the production-related information stored in the production-related information storage unit 12. The fifth index value is calculated based on the information of the power consumption of 3.

Specifically, the index value calculation unit 23 calculates the daily total production amount based on the production amount information included in the production-related information. Further, the index value calculation unit 23 determines the power consumption of the production facility 2 and the power consumption of the related facility 3 on a daily basis based on the information of the power consumption of the production facility 2 and the related facility 3 included in the production-related information. And are added to calculate the total power consumption. The index value calculation unit 23 calculates the fifth index value by dividing the total power consumption by the total production amount on a daily basis. It can be said that the larger the fifth index value is, the more wasteful energy consumption that does not contribute to production increases.

The index value calculation unit 23 can also calculate an index value of a type other than the above-mentioned index. For example, the index value calculation unit 23 can calculate the total power consumption per day, the total production amount per day, the power consumption during the break time, and the like as index values. Further, the index value calculation unit 23 can also integrate the above-mentioned plurality of types of index values and calculate them as one index value. In this case, the index value calculation unit 23 calculates, for example, a value obtained by weighting and adding each index value according to the importance as one index value.

FIG. 6 is a diagram showing an example of a plurality of types of index values calculated by the index value calculation unit according to the first embodiment. In the example shown in FIG. 6, the first index value, the second index value, the third index value, the fourth index value, and the fifth index value are calculated on a daily basis. For example, in "October 20, 2019", the first index value is "15", the second index value is "14", the third index value is "213", and the fourth index value is "213". The index value of is "31", and the fifth index value is "0.37".

The score calculation unit 24 calculates a score indicating the degree of influence of each of the plurality of factor candidates on the energy loss for each index based on the daily index value calculated by the index value calculation unit 23. The score calculation unit 24 generates integrated information in which a plurality of types of index values and a plurality of factor candidates are associated with each other. FIG. 7 is a diagram showing an example of integrated information according to the first embodiment. The integrated information shown in FIG. 7 is information in which the first index value and a plurality of factor candidates are associated with each other, the first index value is set as an objective variable, and the first factor candidate information and the second factor are present. Information on a plurality of factor candidates including candidate information is set as explanatory variables.

Although not shown in FIG. 7, information on factor candidates such as the average value and fluctuation range of each of indoor temperature, humidity, brightness, noise, and vibration is also set as explanatory variables in the integrated information. Further, the score calculation unit 24 generates integrated information similar to the integrated information shown in FIG. 7 for each of the second index value, the third index value, the fourth index value, and the fifth index value. do.

The score calculation unit 24 uses data mining using the above-mentioned integrated information to select a plurality of factor candidates for each of the first index, the second index, the third index, the fourth index, and the fifth index. A score indicating the degree of influence on each energy loss is calculated. Factor candidates with higher scores have a greater effect on energy loss.

The analysis method used in data mining is, for example, regression analysis, clustering, or frequent pattern extraction. In the following, an example in which the score calculation unit 24 calculates the score by the regression analysis will be described, but the score calculation unit 24 can also perform data mining using an analysis method other than the multiple regression analysis.

The score calculation unit 24 performs preprocessing on the factor candidates and determines the value of each explanatory variable. The score calculation unit 24 performs a type of preprocessing according to the factor candidate. The types of preprocessing performed on the factor candidates include a first preprocessing and a second preprocessing. First, the first preprocessing will be described.

The first pre-processing is processing performed on factor candidates that cannot be expressed in quantity. Factor candidates that cannot be expressed in quantity include, for example, "month", "day of the week", "week", "production start time", "production end time", "target model", "person in charge", or "occurrence error". Is.

The score calculation unit 24 represents the "day of the week" with seven types of explanatory variables when the factor candidate is the "day of the week". Specifically, the score calculation unit 24 represents the day of the week with seven types of explanatory variables in which "1" is set when it is the corresponding day of the week among the seven types of days from Sunday to Monday. For example, when the "day of the week" is "Sunday", the score calculation unit 24 sets the value of the explanatory variable corresponding to Sunday to "1" among the seven types of explanatory variables, and sets the values of the other explanatory variables to "1". Set to "0". When the "day of the week" is "Monday", the score calculation unit 24 sets the value of the explanatory variable corresponding to Monday to "1" among the seven types of explanatory variables, and sets the values of the other explanatory variables to "1". Set to "0".

In addition, the score calculation unit 24 represents the "person in charge" with the same number of types of explanatory variables as the number of persons in charge. For example, when the number of persons in charge is four, the score calculation unit 24 represents the “person in charge” with four types of explanatory variables. Further, the score calculation unit 24 represents the "target model" with the same number of explanatory variables as the type of the target model. For example, when the score calculation unit 24 has five types of target models, the score calculation unit 24 represents the “target model” with five types of explanatory variables. Further, the score calculation unit 24 represents the “occurrence error” with the same number of types of explanatory variables as the type of the occurrence error. For example, when the score calculation unit 24 has 10 types of occurrence errors, the score calculation unit 24 represents “occurrence error” with 10 types of explanatory variables.

Next, the second process will be described. The second process is a process performed on a factor candidate that can be represented by a quantity, and the factor candidate that can be represented by a quantity by the second process is represented by one explanatory variable. Candidate factors that can be expressed in quantity are, for example, "average temperature", "temperature fluctuation range", "humidity average value", "humidity fluctuation range", "carbon dioxide average value", and "carbon dioxide fluctuation". Width, "average brightness", and "brightness fluctuation range".

The score calculation unit 24 performs a process of adjusting each explanatory variable so that the average is 0 and the variance is 1, as the second pre-process. Specifically, in the second process, the score calculation unit 24 calculates the average value of the factor candidates for each factor candidate, subtracts the average value of the factor candidates from the value of the factor candidates for each day, and the subtraction result. Is divided by the standard deviation to calculate the value of the explanatory variable. When calculating the score of the factor candidate for the index whose value becomes smaller as the energy loss becomes larger, the score calculation unit 24 reverses the positive / negative of the value of the explanatory variable calculated by the above method. The index in which the energy loss decreases as the value increases is the fourth index value.

The score calculation unit 24 performs multiple regression analysis for each index using the following equation (1). In the following equation (1), "n" is the total number of the above-mentioned explanatory variables, "y" is an index value, and "x ₁ ", "x ₂ ", "x ₃ ", ..., ""x _n " is the value of the explanatory variable, and "a ₁ ", "a ₂ ", "a ₃ ", ..., " _An " is a coefficient.
y = a ₁ x x ₁ + a ₂ x x ₂ + a ₃ x x ₃ + ... an _n x x _n ... (1)

The score calculation unit 24 sets the values of a plurality of explanatory variables set in the integrated information for each index on a daily basis as “x ₁ ”, “x ₂ ”, “x ₃ ”, ..., “X _n ”. Is substituted into, and the difference between the value of "y" obtained by the equation (1) and the value of the target variable set in the integrated information is calculated. Score calculation unit 24, for example, for each index, so that the average value or the total value of the calculated difference is smallest, "a _1", "a _2", "a _3", ..., "a _n ”Optimize.

The score calculation unit 24 calculates the absolute value of each coefficient as the score of the factor candidate for each index. For example, if "x ₁ " is the explanatory variable corresponding to Sunday, the score for Sunday is "a ₁ ". If "x ₂ " is an explanatory variable corresponding to Monday, the score on Monday is "a ₂ ". The absolute value of the coefficient for the factor candidate that can be expressed in quantity is the score. For example, if "x ₃ " is an explanatory variable for the average temperature, the average temperature score is the absolute value of _{"a 3".}

In the above example, the score calculation unit 24 generates integrated information, but it is sufficient if data mining processing can be performed for each index, and it is not necessary to generate integrated information. For example, when the score calculation unit 24 calculates the score of each factor candidate by multiple regression analysis, the score calculation unit 24 sets the index value as the value of the objective variable based on the information obtained from the information generation unit 22 and the index value calculation unit 23. The value of the factor candidate may be the value of the explanatory variable, and is not limited to the above-mentioned example.

The information providing unit 25 shown in FIG. 2 outputs information on two or more factor candidates having a higher score calculated by the score calculating unit 24 for each index. For example, the information providing unit 25 arranges a plurality of factor candidates in descending order of the score calculated by the score calculation unit 24 to generate ranking information representing the plurality of factor candidates in the form of a ranking table, and at least among the generated ranking information. Outputs information on the top two factor candidates. The information providing unit 25 causes the display unit 13 to display the ranking information generation unit 41 that generates the above-mentioned ranking information and the loss factor information including at least a part of the ranking information generated by the ranking information generation unit 41. It includes a display processing unit 42.

For example, the display processing unit 42 causes the display unit 13 to display information including a preset number of factor candidates in descending order of the score among the ranking information in the form of a ranking table. In addition, the display processing unit 42 can display the loss factor information, which is the information in which the factor candidates whose score is equal to or higher than the preset value in the ranking information are expressed in the form of the ranking table, on the display unit 13. In addition, the display processing unit 42 can display all of the ranking information on the display unit 13 in the form of a ranking table. The display processing unit 42 can display the loss factor information on the display unit 13 in a format other than the ranking table format.

FIG. 8 is a diagram showing an example of loss factor information displayed on the display unit by the information providing unit according to the first embodiment. The loss factor information shown in FIG. 8 includes the types and contents of the five factor candidates with the highest scores as the estimation factors of energy loss for the first index.

In the example shown in FIG. 8, the day of the week "Monday" has the highest score for the first index, the target model "A", the week "4th week", the month "March", and the production end time "17:00". It shows that the score is lower in the order of.

As described above, the energy management device 10 has a high degree of influence on energy loss by calculating a score indicating the degree of influence on energy loss of each of the plurality of factor candidates by using the index related to energy consumption in the diagnosis target. Multiple factors can be identified. Further, the energy management device 10 can present to the user information in the form of a ranking table in which a plurality of factor candidates are arranged in order of the degree of influence on energy loss. Therefore, the user can grasp the items having a high influence on the energy loss, and the diagnosis result of the energy management device 10 can be used for the examination of the improvement activity for the energy loss.

In the above example, the score calculation unit 24 calculates the score of each factor candidate for each index, but for each factor candidate, it is possible to calculate the total score which is the total value of the scores of the plurality of indexes. In this case, the ranking information generation unit 41 arranges a plurality of factor candidates in descending order of the total score calculated by the score calculation unit 24, and generates ranking information representing the plurality of factor candidates in the form of a ranking table.

In the above example, the score calculation unit 24 calculates the scores of a plurality of factor candidates for each of the plurality of indicators, but the plurality of indicators are collectively used as an integrated index, and the scores of the plurality of factor candidates are calculated for the integrated index. You can also do it. For example, the score calculation unit 24 multiplies or adds the corresponding coefficients to each of the first index value, the second index value, the third index value, the fourth index value, and the fifth index value. Then, the total value of the multiplication results or the total value of the addition results can be calculated daily as the value of the integrated index. Then, the score calculation unit 24 can calculate the score of each of the plurality of factor candidates for the integrated index by data mining from the value of the integrated index and the value of the plurality of factor candidates.

Next, the processing by the processing unit 11 of the energy management device 10 will be described using a flowchart. FIG. 9 is a flowchart showing an example of processing by the processing unit of the energy management device according to the first embodiment.

As shown in FIG. 9, the processing unit 11 of the energy management device 10 determines whether or not the information collection timing has come (step S10). In step S10, the processing unit 11 determines that the information collection timing has come when the information transmitted from the power sensor 4, the power sensor 5, the production amount sensor 6, the environment sensor 7, or the production control device 8 is received. Further, the processing unit 11 can also determine that the information collection timing has come when the timing arrives at a preset cycle.

When the processing unit 11 determines that the information collection timing has come (step S10: Yes), the processing unit 11 updates the production-related information (step S11). In step S11, the processing unit 11 stores the information transmitted from the power sensor 4, the power sensor 5, the production amount sensor 6, the environment sensor 7, or the production management device 8 in the production-related information storage unit 12. Update production-related information by adding to.

Further, when the information collection timing arrives at a preset cycle, the processing unit 11 sets the power sensor 4, the power sensor 5, the production amount sensor 6, the environment sensor 7, and the production control device 8 in step S11. Request information to be sent to. In this case, the processing unit 11 receives information transmitted from the power sensor 4, the power sensor 5, the production amount sensor 6, the environment sensor 7, and the production control device 8 as requested. The processing unit 11 updates the production-related information by adding the received information to the production-related information stored in the production-related information storage unit 12.

When the processing of step S11 is completed or when it is determined that the information collection timing has not been reached (step S10: No), the processing unit 11 determines whether or not the diagnosis start timing has been reached (step S12). In step S12, the processing unit 11 determines that the diagnosis start timing has come, for example, when the user requests a diagnosis.

When the processing unit 11 determines that the diagnosis start timing has come (step S12: Yes), the processing unit 11 acquires the production-related information from the production-related information storage unit 12 (step S13). Then, the processing unit 11 generates factor candidate information based on the production-related information, calendar information, and the like acquired in step S13 (step S14). Further, the processing unit 11 calculates the daily index value for each index based on the production-related information acquired in step S13 (step S15).

Next, the processing unit 11 calculates the score of each factor candidate for each index based on the factor candidate information generated in step S14 and the index value generated in step S15 (step S16). Based on the score of each factor candidate calculated in step S16, the processing unit 11 generates ranking information for each index in which a plurality of factor candidates are arranged in descending order of score (step S17). Then, the processing unit 11 displays at least a part of the ranking information for each index on the display unit 13 (step S18). In step S18, for example, the processing unit 11 displays the information of the top two or more factor candidates among the ranking information for each index on the display unit 13 in the form of a ranking table.

The processing unit 11 ends the processing shown in FIG. 9 when the processing in step S18 is completed or when it is determined that the diagnosis start timing has not been reached (step S12: No).

FIG. 10 is a diagram showing an example of the hardware configuration of the processing unit of the energy management device according to the first embodiment. As shown in FIG. 10, the processing unit 11 of the energy management device 10 includes a computer including a processor 101, a memory 102, and an input / output interface 103. The input / output interface 103 includes a communication unit that transmits / receives information to / from the

power sensors

4 and 5, the production amount sensor 6, the environment sensor 7, and the production control device 8.

The processor 101, the memory 102, and the input / output interface 103 can send and receive data to and from each other by, for example, the bus 104. Each of a part of the information collecting unit 21 of the processing unit 11 and a part of the display processing unit 42 of the processing unit 11 is realized by the input / output interface 103. The processor 101 executes the functions of the information collection unit 21, the information generation unit 22, the index value calculation unit 23, the score calculation unit 24, and the information provision unit 25 by reading and executing the program stored in the memory 102. .. The processor 101 is, for example, an example of a processing circuit, and includes one or more of a CPU (Central Processing Unit), a DSP (Digital Signal Processor), and a system LSI (Large Scale Integration).

The memory 102 is one or more of RAM (Random Access Memory), ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable Read Only Memory), and EEPROM (registered trademark) (Electrically Erasable Programmable Read Only Memory). include. The memory 102 also includes a recording medium on which a computer-readable program is recorded. Such recording media include one or more of non-volatile or volatile semiconductor memories, magnetic disks, flexible memories, optical disks, compact disks, and DVDs (Digital Versatile Discs). The energy management device 10 may include integrated circuits such as an ASIC (Application Specific Integrated Circuit) and an FPGA (Field Programmable Gate Array).

As described above, the energy management device 10 according to the first embodiment includes an index value calculation unit 23, a score calculation unit 24, and an information providing unit 25. The index value calculation unit 23 calculates one or more types of index values related to energy consumption in the diagnosis target including the production facility 2 based on the production-related information which is the information related to the past production. The score calculation unit 24 is a candidate for each of a plurality of factor candidates that are candidates for energy consumption factors that did not contribute to production in the diagnosis target, based on one or more types of index values calculated by the index value calculation unit 23. Calculate a score that indicates the degree of impact on energy consumption that did not contribute to production. The information providing unit 25 outputs information on two or more factor candidates having the highest score calculated by the score calculation unit 24 among the plurality of factor candidates. As described above, the energy management device 10 has a high degree of influence on the energy consumption that did not contribute to the production by calculating the score indicating the degree of influence on the energy consumption that did not contribute to the production of each of the plurality of factor candidates. Multiple factors can be identified. Further, the energy management device 10 identifies the factors of energy consumption that did not contribute to production without taking the trouble of manually associating the factors of energy consumption that did not contribute to production with the characteristic pattern in advance. be able to.

Further, the diagnosis target includes the related equipment 3 used in connection with the production equipment 2. The production-related information includes information indicating the energy consumption of the production equipment 2, information indicating the energy consumption of the related equipment 3, and information indicating the production amount of the production equipment 2. The index value calculation unit 23 calculates one or more types of index values based on the information indicating the energy consumption of the production equipment 2, the information indicating the energy consumption of the related equipment 3, and the information indicating the production amount of the production equipment 2. .. As described above, since the energy management device 10 treats the energy consumption of the related equipment 3 as a factor of energy consumption that does not contribute to production, for example, the energy consumption of the entire production facility 1 that does not contribute to production Information useful for improvement activities can be provided to users.

Further, the index value calculated by the index value calculation unit 23 is at least one of a first index value, a second index value, a third index value, a fourth index value, and a fifth index value. including. The first index value indicates the time from when the production equipment 2 is turned on until the production of the production equipment 2 is started. The second index value indicates the time from the end of production by the production equipment 2 until the production equipment 2 is turned off. The third index value indicates the difference between the time when the related equipment 3 is on and the time when the production equipment 2 is on. The fourth index value indicates the ratio of the time during which the production facility 2 is in production to the time during which the production facility 2 is on. The fifth index value indicates the energy consumption of the diagnosis target per unit production amount by the production equipment 2. In this way, the energy management device 10 can provide the user with useful information for energy consumption improvement activities that do not contribute to production from the viewpoint of easy grasping.

Further, the energy management device 10 includes an information generation unit 22 that generates information on a plurality of factor candidates based on production-related information. The score calculation unit 24 determines the production of each of the plurality of factor candidates based on the plurality of types of index values calculated by the index value calculation unit 23 and the information of the plurality of factor candidates generated by the information generation unit 22. Calculate a score that indicates the degree of impact on energy consumption that did not contribute. In this way, since the energy management device 10 generates information on a plurality of factor candidates in the production-related information, the load on the user can be significantly reduced as compared with the case where the information on the plurality of factor candidates is manually input. Can be done.

In addition, a plurality of factor candidates include the day, week, and month of the day when the goods were produced by the production equipment 2, the person in charge of production, the type of goods produced by the production equipment 2, the error that occurred in the production equipment 2, and the error that occurred in the production equipment 2. Includes two or more of the environments of production equipment 2. As a result, the energy management device 10 has a plurality of factors having a high influence on energy consumption that did not contribute to production from the viewpoint of time, human, production target, production equipment 2, or environment. Can be identified.

Further, the score calculation unit 24 calculates the score of each of the plurality of factor candidates for each of the plurality of types of index values. The information providing unit 25 outputs information on two or more factor candidates having a higher score calculated by the score calculation unit 24 among the plurality of factor candidates for each of the plurality of types of index values. As described above, since the energy management device 10 uses a plurality of indexes, it is possible to provide the user with useful information for energy consumption improvement activities that do not contribute to production from each of the plurality of viewpoints.

Further, the information providing unit 25 outputs ranking information representing a preset number of factor candidates in the form of a ranking table in order from the factor candidates having the highest score among the plurality of factor candidates. As a result, the energy management device 10 can provide the user with information on a plurality of factors having a high influence on energy consumption that did not contribute to production in the form of a ranking table.

Embodiment 2.
The energy management device according to the second embodiment corrects the score based on the contribution of each of the plurality of factor candidates to the user's improvement activity for the energy consumption that does not contribute to the production. It is different from the management device 10. In the following, components having the same functions as those in the first embodiment are designated by the same reference numerals and the description thereof will be omitted, and the differences from the energy management device 10 of the first embodiment will be mainly described.

FIG. 11 is a diagram showing an example of the configuration of the energy management device according to the second embodiment. As shown in FIG. 11, the energy management device 10A according to the second embodiment is provided with an input unit 14 and a contribution information storage unit 15, and is provided with a processing unit 11A in place of the processing unit 11. It is different from the energy management device 10 of the first embodiment. The input unit 14 is, for example, an input device such as a keyboard, a mouse, or a touch panel of a mobile terminal.

The processing unit 11A includes a contribution estimation unit 26. Further, the processing unit 11A includes an information providing unit 25A instead of the information providing unit 25. The contribution estimation unit 26 estimates the contribution of each of the plurality of factor candidates to the improvement activity by the user for the energy consumption that does not contribute to production, based on the information input by the input unit 14. The contribution estimation unit 26 stores information indicating the contribution of each of the estimated plurality of factor candidates in the contribution information storage unit 15.

The information providing unit 25A includes a ranking information generating unit 41A and a display processing unit 42A. The ranking information generation unit 41A is a factor candidate corresponding to a plurality of factor candidates based on the contribution of each of the plurality of factor candidates estimated by the contribution estimation unit 26 and stored in the contribution information storage unit 15. Correct the score. The ranking information generation unit 41A generates ranking information based on the corrected score.

The display processing unit 42A causes the display unit 13 to display loss factor information including an input box for inputting a user's evaluation, in addition to the types and contents of a plurality of higher-order estimation factors. FIG. 12 is a diagram showing an example of loss factor information displayed on the display unit by the information providing unit according to the second embodiment.

The loss factor information shown in FIG. 12 includes, in addition to the contents of the loss factor information shown in FIG. 8, an input box for inputting a user's evaluation for each of a plurality of factor candidates. Specifically, the factor information includes a first input box corresponding to "useful" and a second input box corresponding to "useless" for each of the plurality of factor candidates. The user inputs a check mark in the first input box corresponding to the factor candidate considered to be useful, and inputs a check mark in the second input box corresponding to the factor candidate considered to be useless. The check mark is performed by, for example, a mouse click operation or a touch operation on the touch panel.

The contribution estimation unit 26 estimates the contribution of each factor candidate to the user's activity for energy consumption that does not contribute to production, based on the input history of each factor candidate in the first input box or the second input box. For example, the contribution estimation unit 26 estimates the contribution of each factor candidate to the user's activity for energy consumption that does not contribute to production by using the following equation (2). In the following formula (2), "Z" is the degree of contribution to the user's activity for energy consumption that does not contribute to production, "α" is a coefficient larger than 1, and "β" is a coefficient less than 1. .. Further, in the following formula (2), "N" is the number of times the user has entered a check mark in the first input box in the past, and "M" is the number of times the user has entered a check mark in the second input box in the past. The number of times it was done.
Z = α ^N × β ^M ... (2)

The larger the contribution Z, the higher the degree of usefulness for the user's improvement activities for energy consumption that does not contribute to production. The contribution estimation unit 26 can also estimate the user's contribution to each factor candidate by machine learning instead of calculating the contribution by the above equation (2).

The method of inputting the evaluation by the user is not limited to the first input box and the second input box, and is, for example, a method of selecting and inputing one of "useful" and "useless" in the selection box. May be good. Further, the evaluation by the user is not limited to two types of "useful" and "not useful", and may be selected and input from three or more levels of information. In addition, the evaluation by the user may be input by a numerical value indicating the degree of usefulness.

The ranking information generation unit 41A acquires information indicating the contribution degree of each of the plurality of factor candidates estimated by the contribution degree estimation unit 26 from the contribution degree information storage unit 15. The ranking information generation unit 41A multiplies each score of the plurality of factor candidates calculated by the score calculation unit 24 by the contribution of the corresponding factor candidate among the contributions of the plurality of factor candidates. Correct the score of each of the factor candidates.

For example, assume that the factor candidate is "Monday", the score of "Monday" is "0.2", and the contribution of "Monday" is "3". In this case, the ranking information generation unit 41A corrects the score of "Monday" from "0.2" to "0.6" by multiplying "0.2" by "3". It can be said that the corrected score quantifies the degree of usefulness for the user's improvement activities for energy consumption that does not contribute to production.

The ranking information generation unit 41A arranges a plurality of factor candidates in descending order of the corrected score as described above, and generates ranking information representing the plurality of factor candidates in a ranking format. The display processing unit 42A displays on the display unit 13 the loss factor information including at least a part of the ranking information generated by the ranking information generation unit 41A and the information of the first input box and the second input box described above. Display it. For example, the ranking information generation unit 41A causes the display unit 13 to display the loss factor information shown in FIG.

As described above, the score calculation unit 24 can also calculate the scores of each of the plurality of factor candidates for the integrated index. In this case, the score calculation unit 24 multiplies each score of the plurality of factor candidates with respect to the integrated index by the contribution of the corresponding factor candidate among the contributions of the plurality of factor candidates, so that each of the plurality of factor candidates Correct the score. The ranking information generation unit 41A generates ranking information based on the respective scores of the plurality of factor candidates after correction for the integrated index.

As described above, the energy management device 10A can identify a plurality of factors having a high degree of influence on energy consumption that do not contribute to production, similarly to the energy management device 10. Further, the energy management device 10A can preferentially provide the user with a factor candidate having a high degree of contribution to the user's improvement activity with respect to energy consumption that does not contribute to production. As a result, the user can grasp the factors that are highly effective for the user's improvement activity for energy consumption that does not contribute to production, and can use it for studying the energy consumption improvement activity that does not contribute to production.

Next, the processing by the processing unit 11A of the energy management device 10A will be described using a flowchart. FIG. 13 is a flowchart showing an example of processing by the processing unit of the energy management device according to the second embodiment. Since the processes of steps S20 to S22 shown in FIG. 13 are the same as the processes of steps S10 to S12 shown in FIG. 9, the description thereof will be omitted.

As shown in FIG. 13, when the processing unit 11A of the energy management device 10A determines that the diagnosis start timing has come (step S22: Yes), the processing unit 11A performs the diagnosis process (step S23). The process of step S23 is the process of steps S30 to S36 shown in FIG. 14, which will be described in detail later.

The processing unit 11A determines whether or not there is a user input when the processing in step S23 is completed or when it is determined that the diagnosis start timing has not been reached (step S22: No) (step S24). In step S24, the processing unit 11A, for example, when a check mark is input to the first input box corresponding to "useful" or the second input box corresponding to "useless" shown in FIG. It is determined that there is an input of.

When the processing unit 11A determines that the user has input (step S24: Yes), the processing unit 11A contributes each factor candidate to the user's improvement activity for energy loss, which is energy consumption that does not contribute to production, based on the user's input history. The degree is calculated (step S25). Then, the processing unit 11A stores the calculated information indicating the contribution degree of each factor candidate in the contribution degree information storage unit 15 (step S26).

The processing unit 11A ends the processing shown in FIG. 13 when the processing in step S26 is completed or when it is determined that there is no user input (step S24: No).

FIG. 14 is a flowchart showing an example of diagnostic processing by the processing unit of the energy management device according to the second embodiment. Since the processes of steps S30 to S33 shown in FIG. 14 are the same as the processes of steps S13 to S16 shown in FIG. 9, the description thereof will be omitted.

When the processing of steps S30 to S33 is completed, the processing unit 11A corrects each of the scores of the plurality of factor candidates based on the contribution of the corresponding factor candidates (step S34). Then, the processing unit 11A generates ranking information for each index based on the corrected score for each index (step S35). In step S35, the processing unit 11A generates ranking information for each index in which a plurality of factor candidates are arranged in descending order of score based on the score of each factor candidate corrected in step S34.

In step S35, the processing unit 11A generates ranking information in which a plurality of factor candidates are arranged in descending order of the corrected score based on the score of each factor candidate corrected in step S34. Then, the processing unit 11A displays at least a part of the ranking information generated in step S35 on the display unit 13 (step S36), and ends the process shown in FIG.

An example of the hardware configuration of the processing unit 11A of the energy management device 10A according to the second embodiment is the same as the hardware configuration of the processing unit 11 of the energy management device 10 shown in FIG. The processor 101 reads and executes the program stored in the memory 102, thereby causing the information collection unit 21, the information generation unit 22, the index value calculation unit 23, the score calculation unit 24, the information provision unit 25A, and the contribution estimation unit. Twenty-six functions can be performed.

As described above, the energy management device 10A according to the second embodiment includes a contribution estimation unit 26. The contribution estimation unit 26 estimates the contribution of each of the plurality of factor candidates to the user's improvement activities for energy consumption that does not contribute to production. The information providing unit 25A corrects the score of the corresponding factor candidate among the plurality of factor candidates based on the contribution of each of the plurality of factor candidates estimated by the contribution estimation unit 26, and based on the corrected score. , Generate ranking information. Thereby, for example, the energy management device 10A can preferentially provide the user with a factor candidate having a high degree of contribution to the user's improvement activity with respect to energy consumption that does not contribute to production. Therefore, the user can grasp the factors that are highly effective for the user's improvement activity for energy consumption that does not contribute to production, and can use it for studying the energy consumption improvement activity that does not contribute to production.

Embodiment 3.
The energy management system according to the third embodiment is learning to input information of one or more kinds of index values based on the information obtained from the energy management device and output the scores of candidates of energy consumption factors that did not contribute to production. It has a server that generates a model. In the following, the components having the same functions as those of the second embodiment will be designated by the same reference numerals and the description thereof will be omitted, and the differences from the second embodiment will be mainly described.

FIG. 15 is a diagram showing an example of the configuration of the energy management system according to the third embodiment. As shown in FIG. 15, the energy management system 200 according to the third embodiment includes

energy management devices

10B ₁ , 10B ₂ , 10B ₃ , a server 50, and a mobile terminal 60. The

energy management devices

10B ₁ , 10B ₂ , and 10B ₃ have the same configuration as each other. In the following, when each of the

energy management devices

10B ₁ , 10B ₂ , and 10B ₃ is shown without distinction, it is described as the energy management device 10B. May be done.

Like the energy management device 10A, each energy management device 10B is connected to a power sensor, a production volume sensor, an environment sensor, a production control device, and the like (not shown), and these power sensors, a production volume sensor, an environment sensor, and the like. Collect information from production control equipment. Each energy management device 10B associates the collected information with the time at the time of collection and adds it to the production-related information. The power sensor, the production amount sensor, the environmental sensor, and the production management device connected to the energy management device 10B are provided in different production facilities 1 for each energy management device 10B.

Similar to the energy management device 10A, the energy management device 10B generates factor candidate information including a plurality of factor candidate information that is a candidate for a factor that causes energy loss based on production-related information. Further, the energy management device 10B calculates one or more types of index values related to energy consumption in a diagnosis target including production equipment (not shown) and related equipment, similarly to the energy management device 10A. Further, the energy management device 10B, like the energy management device 10A, calculates a score indicating the degree of influence of each of the plurality of factor candidates on the energy loss for each index.

The energy management device 10B transmits learning information to the server 50. The learning information includes information on one or more types of index values, information on scores of each factor candidate for each index, and identification information on the energy management device 10B. In the following, the score of the factor candidate may be described as the factor score. The score of the factor candidate included in the learning information is a score calculated by the score calculation unit 24, but may be a score corrected by the ranking information generation unit 41A.

The server 50 is connected to the energy management device 10B and the mobile terminal 60 via a network (not shown), and transmits / receives information between the energy management device 10B and the mobile terminal 60. The network (not shown) is, for example, a WAN (Wide Area Network) such as the Internet, but may be a network such as a LAN (Local Area Network).

The server 50 acquires learning information from the energy management device 10B that stores production-related information in an amount sufficient to calculate the factor score, and based on the acquired learning information, one or more types of indexes. Generate a trained model that inputs value information and outputs multiple factor scores.

Then, the server 50 acquires the diagnosis target information including the information of one or more kinds of index values from the energy management device 10B which does not store the production-related information of an amount of information sufficient for calculating the factor score. The energy management device 10B that does not store a sufficient amount of production-related information for calculating the factor score is, for example, a production in which the energy management device 10B newly installed in the production facility 1 or a new facility is installed. It is an energy management device 10B installed in the facility 1.

The server 50 calculates a plurality of factor scores based on the diagnosis target information acquired from the energy management device 10B and the trained model information generated by learning based on the learning information, and the calculated factor score is higher. The diagnosis result information including the information of two or more factor candidates is transmitted to the mobile terminal 60 or the energy management device 10B that has transmitted the diagnosis target information.

The mobile terminal 60 is, for example, a smartphone, a tablet, a notebook computer, or the like, and displays information on two or more top factor candidates based on the diagnosis result information transmitted from the server 50. Further, the processing unit 11B of the energy management device 10B that has transmitted the diagnosis target information displays the information of the upper two or more factor candidates on the display unit 13 based on the diagnosis result information transmitted from the server 50.

In this way, the server 50 calculates the factor score for one or more types of indicators based on the information from the energy management device 10B that does not store the production-related information in an amount sufficient to calculate the factor score. Then, the diagnosis result information including the information of the two or more factor candidates whose calculated factor scores are high is provided.

Therefore, the server 50 may not sufficiently collect production-related information about the equipment to be diagnosed, for example, within a few days after the energy management device 10B is introduced. However, it is possible to identify a plurality of factors that have caused energy consumption that does not contribute to production, based on the information of the diagnosed equipment for which the diagnosis has already been completed. Hereinafter, the configurations of the energy management device 10B and the server 50 will be specifically described.

FIG. 16 is a diagram showing an example of the configuration of the energy management device according to the third embodiment. As shown in FIG. 16, the energy management device 10B according to the third embodiment includes the processing unit 11B instead of the processing unit 11, and further includes the communication unit 16, and the energy management according to the second embodiment. Different from device 10A. The communication unit 16 transmits / receives information to / from the server 50 via a network (not shown).

The processing unit 11B is different from the processing unit 11A according to the second embodiment in that the information providing unit 25B is provided instead of the information providing unit 25A. The information providing unit 25B provides information on one or more types of index values calculated by the index value calculation unit 23, score information for each index of a plurality of factor candidates calculated by the score calculation unit 24, and energy management. The learning information including the identification information of the device 10B is generated. The information providing unit 25B transmits the generated learning information to the server 50 via the communication unit 16.

Further, when the amount of information of the production-related information stored in the production-related information storage unit 12 is not sufficient for calculating the factor score, the information providing unit 25B has one or more types of indexes calculated by the index value calculation unit 23. The diagnosis target information including the value information is transmitted to the server 50 via the communication unit 16. In the following, it is assumed that the amount of information of the production-related information stored in the production-related information storage unit 12 of the energy management device 10B ₃ is not sufficient for calculating the factor score, and the production-related information storage of the _{energy management devices 10B 1} and 10B _{2 is performed.} In some cases, the amount of production-related information stored in unit 12 is sufficient to calculate the factor score.

FIG. 17 is a diagram showing an example of the configuration of the server according to the third embodiment. As shown in FIG. 17, the server 50 according to the third embodiment includes a communication unit 51, an information acquisition unit 52, a factor estimation unit 53, and a storage unit 54. The communication unit 51 transmits / receives information to / from the energy management device 10B and the mobile terminal 60 via a network (not shown).

The information acquisition unit 52 acquires information such as learning information or diagnosis target information transmitted from the energy management device 10B and received by the communication unit 51. The information acquisition unit 52 stores the information acquired from the energy management device 10B in the storage unit 54, or outputs the information to the factor estimation unit 53.

When the learning information is acquired by the information acquisition unit 52, the factor estimation unit 53 learns the factors that caused energy consumption that does not contribute to production in the diagnosed equipment based on the learning information, and performs a learning model. To generate. The diagnosed equipment is a production equipment in which sufficient production-related information is accumulated to estimate the factors that caused energy consumption in the energy management device 10B. For example, the diagnosis of the _{energy management devices 10B 1} and 10B _{2 is performed.} This is the target equipment.

Further, when the diagnosis target information is acquired by the information acquisition unit 52, the factor estimation unit 53 causes a plurality of energy consumptions that do not contribute to production in the diagnosis target equipment based on the diagnosis target information and the learned model 57. Estimate the factors. Diagnosed facility, for example, a newly installed equipment production facility 1, which is diagnosed equipment from energy management device 10B _3.

The factor estimation unit 53 includes a model generation unit 55 and an inference unit 56. The model generation unit 55 performs learning based on the input information and the label information obtained based on the learning information output from the information acquisition unit 52, and generates a trained model that estimates an appropriate output from the input information. The input information is information on one or more types of index values, and the label information is information on the score for each index of the plurality of factor candidates.

The model generation unit 55 performs learning by supervised learning using, for example, a neural network model. Here, in supervised learning, learning information including a set of input information and result information called a label is given to a learning device to learn the characteristics of the learning information, and the result is obtained from the input. A method of inferring. The set of input information and label information is also called a dataset.

A neural network is composed of an input layer composed of a plurality of neurons, an intermediate layer composed of a plurality of neurons, and an output layer composed of a plurality of neurons. The intermediate layer may be one layer or two or more layers. The middle layer is also called the hidden layer.

FIG. 18 is a diagram showing an example of the neural network according to the third embodiment. The neural network shown in FIG. 18 is a three-layer neural network, and includes input layers X1, X2, X3, intermediate layers Y1, Y2, and output layers Z1, Z2, Z3.

When a plurality of input values included in the input information are input to the input layers X1, X2, X3, the weight W1 is multiplied by the plurality of input values, and the plurality of input values multiplied by the weight W1 are the intermediate layers Y1, Y2. Is entered in. The weight W1 includes w11, w12, w13, w14, w15, w16.

In the intermediate layers Y1 and Y2, an operation based on a plurality of input values multiplied by the weight W1 is performed, and the calculation result of the intermediate layers Y1 and Y2 is multiplied by the weight W2 and input to the output layers Z1, Z2 and Z3. .. The weight W2 includes w21, w22, w23, w24, w25, w26.

In the output layers Z1, Z2 and Z3, an operation is performed based on a plurality of values obtained by multiplying the operation results of the intermediate layers Y1 and Y2 by the weight W2, and the operation results are output from the output layers Z1, Z2 and Z3. The output result of the neural network depends on the values of the weights W1 and W2.

Returning to FIG. 17, the explanation of the configuration of the server 50 will be continued. For example, when the learning information having an amount of information equal to or larger than the preset amount of information is acquired by the information acquisition unit 52, the model generation unit 55 executes the above-mentioned learning using the learning information. Generate the trained model 57. The model generation unit 55 stores the generated learned model 57 in the storage unit 54.

The model generation unit 55 generates a trained model 57 that inputs information on one or more types of index values and outputs factor scores of a plurality of factor candidates. The information of one or more kinds of index values includes, for example, information on the sampling period and information on the input index value. In this case, the model generation unit 55 performs learning using the sampling period information and the input index value information as input information and the plurality of factor score information as label information.

The input index value is, for example, a value obtained by averaging each of the first index value, the second index value, the third index value, the fourth index value, and the fifth index value in the sampling period. The plurality of factor scores indicated by the label information are, for example, energy management for each of the first index value, the second index value, the third index value, the fourth index value, and the fifth index value. A plurality of factor scores calculated by the device 10B are added for each factor candidate.

The sampling period information and the input index value information may be generated by the energy management device 10B and included in the learning information, and a model is generated based on the learning information transmitted from the energy management device 10B. It may be generated by part 55.

In the above-mentioned example, an example of using a neural network is given as an example of the learning method of the model generation unit 55, but the learning method of the model generation unit 55 is not limited to the above-mentioned example, and is, for example, genetic programming or. It may be a learning method such as a support vector machine.

The reasoning unit 56 generates the diagnosis target information obtained from the energy management device 10B for diagnosing the energy consumption factor of the new diagnosis target equipment or the information based on the diagnosis target information, and the trained model 57 generated by the model generation unit 55. Enter in.

For example, when the diagnosis target information includes the sampling period information and the input index value information, the inference unit 56 learns the sampling period information and the input index value information included in the diagnosis target information. Enter in 57.

Further, when the diagnosis target information does not include the sampling period information and the input index value, the inference unit 56 includes a first index value, a second index value, and a third index value indicated by the diagnosis target information. A value obtained by averaging each of the fourth index value and the fifth index value in a preset sampling period is calculated as an input index value. The inference unit 56 inputs the calculated input index value information and the sampling period information into the trained model 57.

The inference unit 56 determines information on two or more factor candidates having the highest factor scores based on the factor scores output from the trained model 57 among the plurality of factor candidates. The inference unit 56 outputs high-ranking factor information, which is information on two or more factor candidates having high-ranking factor scores. The higher-level factor information output from the inference unit 56 is transmitted by the communication unit 51 to the mobile terminal 60 or the energy management device 10B that has transmitted the diagnosis target information.

Note that the input index value may be an integrated index value that is a collection of a plurality of types of index values instead of the average value of each of the plurality of types of index values. For example, the integrated index value may be a value obtained by integrating a weighted value for each of a plurality of types of index values, for example, a value obtained by multiplying each of the plurality of types of index values by a coefficient. Further, the information of the input index value may be the information of one kind of index value.

Further, in the above-mentioned example, the input information includes the sampling period information, but when the sampling period is a predetermined fixed sampling period, the input information does not have to include the sampling period information. ..

In this way, the server 50 learns using the learning information output from the _{energy management devices 10B 1} and 10B ₂ that collect sufficient production-related information for diagnosing the energy consumption factor of the production equipment 2. Generates the trained model 57 by. Then, the server 50 uses the trained model 57 to estimate the factors with a high improvement effect among the factors of energy consumption that did not contribute to the production in the equipment to be diagnosed in which the collection of production-related information is not sufficiently collected. do. As a result, the server 50 can provide information that can be useful for examining energy consumption improvement activities even for the equipment to be diagnosed for which the collection of production-related information is not sufficiently collected.

Next, the processing by the processing unit 11B of the energy management device 10B will be described using a flowchart. FIG. 19 is a flowchart showing an example of processing by the processing unit of the energy management device according to the third embodiment. Since the processing of steps S40, S41, S44 to S48, S50, and S51 shown in FIG. 19 is the same as the processing of steps S10 to S18 shown in FIG. 9, the description thereof will be omitted.

As shown in FIG. 19, the processing unit 11B of the energy management device 10B determines whether or not the diagnosis target information transmission timing has come after the production-related information is updated in step S41 (step S42). The diagnosis target information transmission timing is, for example, a timing that occurs every preset sampling period when the amount of information related to production is less than the amount of information for generating ranking information.

When the processing unit 11B determines that the diagnosis target information transmission timing has come (step S42: Yes), the processing unit 11B generates and transmits the diagnosis target information (step S43). In the process of step S43, the processing unit 11B includes information on one or more types of index values related to energy consumption in the diagnostic target including the production equipment based on the production-related information stored in the production-related information storage unit 12. The diagnosis target information is generated, and the generated diagnosis target information is transmitted to the server 50 via the communication unit 16.

The processing unit 11B performs the processing of step S44 when the processing of step S43 is completed or when it is determined that the diagnosis target information transmission timing has not been reached (step S42: No).

In step S48, the processing unit 11B calculates the score of each factor candidate for each index, and then the information of one or more types of index values calculated in step S47 and the score of each factor candidate for each index calculated in step S48. The learning information including the information is transmitted to the server 50 via the communication unit 16 (step S49).

Subsequently, the learning process and the inference process by the server 50 will be described using a flowchart. FIG. 20 is a flowchart showing an example of the learning process by the server according to the third embodiment. As shown in FIG. 20, the information acquisition unit 52 of the server 50 acquires learning information from the energy management device 10B (step S60). In step S60, the information acquisition unit 52 acquires learning information from _{, for example, the energy management device 10B 1} and the energy management device 10B _2.

Next, the model generation unit 55 of the factor estimation unit 53 on the server 50 executes a learning process to generate the learned model 57 based on the learning information acquired by the information acquisition unit 52 (step S61). In the process of step S61, when the learning information acquired by the information acquisition unit 52 does not include the sampling period information and the input index value information, the model generation unit 55 learns acquired by the information acquisition unit 52. Generates sampling period information and input index value information based on the information. The model generation unit 55 uses the information of the sampling period and the information of the input index value as the input information and the information of each factor score as the label information, and performs learning by so-called supervised learning to generate the learned model 57.

The model generation unit 55 of the factor estimation unit 53 generates the trained model 57, stores the information of the generated trained model 57 in the storage unit 54 (step S62), and ends the process shown in FIG.

FIG. 21 is a flowchart showing an example of inference processing by the server according to the third embodiment. As shown in FIG. 21, the information acquisition unit 52 of the server 50 acquires the diagnosis target information from the energy management device 10B (step S70). In step S70, the information acquisition unit 52 acquires the diagnosis target information from _{, for example, the energy management device 10B 3.}

Next, the factor estimation unit 53 calculates a plurality of factor scores based on the diagnosis target information acquired by the information acquisition unit 52 and the information of the learned model 57 stored in the storage unit 54 (step S71). .. In the process of step S71, the factor estimation unit 53 inputs the diagnosis target information acquired by the information acquisition unit 52 or the information based on the diagnosis target information into the trained model 57, and the trained model is calculated by the calculation of the trained model 57. A plurality of factor scores output from 57 are acquired. The diagnosis target information or the information based on the diagnosis target information includes sampling period information and input index value information.

Next, the factor estimation unit 53 estimates two or more factor candidates having the highest factor scores as factors having a high improvement effect based on the factor scores calculated in step S71 among the plurality of factor candidates (step S72). .. The factor estimation unit 53 transmits the estimated factor information having a high improvement effect to the mobile terminal 60 via the communication unit 51 (step S73), and ends the process of FIG. 21.

FIG. 22 is a flowchart showing an example of processing by the mobile terminal according to the third embodiment. _{As shown in FIG. 22, when the identification number of the energy management device 10B 3} of the equipment to be diagnosed is input by the operation of the operation unit (not shown) by the user, the mobile terminal 60 has the identification number of the energy management device 10B ₃ . A diagnostic request including the above is transmitted to the server 50 (step S80). The server 50 that has received the diagnosis request _{executes the inference process shown in FIG. 21 based on the diagnosis target information of the energy management device 10B 3} , and transmits the higher-level factor information obtained by the inference process to the mobile terminal 60.

The mobile terminal 60 receives the higher-level factor information transmitted from the server 50 in response to the transmission of the diagnosis request to the server 50 (step S81). Then, the mobile terminal 60 displays the received higher-level factor information on a display unit (not shown) (step S82), and ends the process shown in FIG. 22.

As a result, the user of the mobile terminal 60 has an improvement effect among a plurality of factor candidates that are candidates for energy consumption factors that did not contribute to production in the equipment to be diagnosed in which the collection of production-related information is not sufficiently collected. It is possible to grasp the information of the factor candidates with high.

In this way, the factor estimation unit 53 of the server 50 according to the third embodiment learns learning information based on the index value information of the diagnosed equipment and the factor score information, and makes a diagnosis at the time of estimation after learning. The factor is estimated by inputting the target information or the information based on the diagnosis target information. The diagnosis target information input to the factor estimation unit 53 may be input to the server 50 by the user using the diagnosis result in the same organization, or may be input to the server 50 by the provider of the energy management device 10B through a cloud service or the like. It can also be input to the server 50.

An example of the hardware configuration of the processing unit 11B of the energy management device 10B according to the third embodiment is the same as the hardware configuration of the processing unit 11 of the energy management device 10 shown in FIG. The processor 101 can execute the function of the processing unit 11B by reading and executing the program stored in the memory 102.

FIG. 23 is a diagram showing an example of the hardware configuration of the server according to the third embodiment. As shown in FIG. 23, the server 50 includes a computer including a processor 201, a memory 202, and a communication device 203. The storage unit 54 is realized by the memory 202. The communication unit 51 is realized by the communication device 203. The processor 201, the memory 202, and the communication device 203 can send and receive data to and from each other by, for example, the bus 204. The processor 201 executes the functions of the information acquisition unit 52 and the factor estimation unit 53 by reading and executing the program stored in the memory 202. The processor 201 is, for example, an example of a processing circuit, and includes one or more of a CPU, a DSP, and a system LSI.

The memory 202 includes one or more of RAM, ROM, flash memory, EPROM, and EEPROM. The memory 202 also includes a recording medium on which a computer-readable program is recorded. Such recording media include one or more of non-volatile or volatile semiconductor memories, magnetic disks, flexible memories, optical discs, compact disks, and DVDs. The server 50 may include integrated circuits such as ASIC and FPGA.

As described above, the server 50 according to the third embodiment includes the model generation unit 55. The model generation unit 55 generates a trained model 57 that inputs information on one or more types of index values and outputs a plurality of factor scores based on the learning information. The learning information includes information on one or more types of index values and information on factor scores, which are scores of each of a plurality of factor candidates. As a result, the server 50 can generate a trained model 57 that outputs information on a plurality of factor scores from information on one or more types of index values.

Further, the server 50 includes an inference unit 56. The inference unit 56 inputs information on one or more types of index values related to energy consumption in the diagnosis target of other

energy management devices

10B ₃ _{different from the energy management devices 10B 1} and 10B _{2 into the trained model 57, and is a trained model.} Based on the information output from 57, the top two or more factor candidates among the plurality of factor candidates are determined. As a result, the server 50 has already completed the diagnosis even when the collection of production-related information regarding the equipment to be diagnosed is not sufficient, for example, within a few days after the _{energy management device 10B 3 is introduced.} It is possible to estimate the improvement factors that can be expected to be effective by referring to the information on the diagnosed equipment.

Further, the server 50 includes a communication unit 51 that transmits information of two or more upper factor candidates determined by the inference unit 56 to the energy management device 10B _{3 or the mobile terminal 60.} The mobile terminal 60 is an example of an external device. As a result, the server 50 can provide the user with useful information for energy consumption improvement activities that do not contribute to production.

Embodiment 4.
The server of the energy management system according to the fourth embodiment generates a radar chart using the degree of variation of a plurality of types of index values, and normalizes one or more types of index values and normalizes one or more types of indexes. It differs from the server 50 according to the third embodiment in that the value information is used in the learning process and the inference process. In the following, components having the same functions as those in the third embodiment will be designated by the same reference numerals and description thereof will be omitted, and the differences from the third embodiment will be mainly described.

FIG. 24 is a diagram showing an example of the configuration of the energy management system according to the fourth embodiment. The energy management system 200A shown in FIG. 24 is different from the energy management system 200 according to the third embodiment in that the server 50A is provided instead of the server 50.

The server 50A determines the degree of variation among a plurality of types of index values based on the learning information of the energy management device 10B in which the collection of production-related information is sufficiently collected, and corresponds to each of the plurality of types of indexes. A radar chart showing information on the top two or more factor candidates and information on the degree of variation in index values is generated. As a result, the server 50A can present to the user information such as a radar chart that allows the user to intuitively grasp the degree of mutual influence between the indexes.

Further, the server 50A normalizes one or more types of index values indicated by the learning information of the energy management device 10B in which the collection of production-related information is sufficiently collected, and is based on the normalized one or more types of index values. And perform the learning process. Further, the server 50A normalizes each index value indicated by the diagnosis target information of the energy management device 10B for which the collection of production-related information is not sufficiently collected, and is based on the information of one or more types of normalized index values. , Performs inference processing.

As a result, the server 50A distributes index values having different possible ranges among the plurality of energy management devices 10B even if the features or usage conditions of the equipment to be diagnosed differ among the plurality of energy management devices 10B. Units can be compared on the same scale. Therefore, the server 50A can accurately estimate the improvement factor that can be expected to be effective by referring to the information of the diagnosed equipment for which the diagnosis has already been completed.

FIG. 25 is a diagram showing an example of the configuration of the server according to the fourth embodiment. As shown in FIG. 25, the server 50A according to the fourth embodiment includes a factor estimation unit 53A instead of the factor estimation unit 53, and further includes an index normalization unit 58 and a radar chart generation unit 59. It is different from the server 50 according to the third embodiment. First, the index normalization unit 58 and the radar chart generation unit 59 will be described.

The index normalization unit 58 normalizes each index value having a different unit and possible range of values. The index normalization unit 58, for example, normalizes a plurality of types of index values indicated by the information acquired by the information acquisition unit 52 to generate a plurality of types of normalization index values.

For example, the index normalization unit 58 normalizes a plurality of types of index values indicated by the learning information acquired by the information acquisition unit 52 to generate a plurality of types of first normalization index values. Further, the index normalization unit 58 normalizes a plurality of types of index values indicated by the diagnosis target information to generate a plurality of types of second normalization index values.

In addition, the index normalization unit 58 calculates the degree of variation of the index value in the index value normalization process. For example, the index normalization unit 58 calculates the degree of variation of the index value included in the information acquired by the information acquisition unit 52 for each index by the determination algorithm shown in the following equation (3). For example, the index normalization unit 58 calculates the degree of variation in the index values for each of the first index, the second index, the third index, the fourth index, and the fifth index.
Degree of variation of index value = {maximum value-minimum value} / average value ... (3)

In the above formula (3), the "minimum value" is the minimum index value among the plurality of index values for the same index, and the "maximum value" is the maximum of the plurality of index values for the same index. It is an index value, and the "average value" is an average value of a plurality of index values for the same index.

The index normalization unit 58 evaluates the degree of variation in the index value in, for example, five stages in order for the radar chart generation unit 59 to generate a radar chart. For example, it is assumed that the degree of variation of the index value calculated by the above formula (3) takes a value from 1 to 100, and the variation of the index value is evaluated by the index normalization unit 58 on a 5-point score.

In this case, if the degree of variation of the index value is in the range of "1 to 20", the index normalization unit 58 sets the score of the 5-grade evaluation to "5" and the degree of variation of the index value is "21 to 40". If it is in the range, the score of the 5-grade evaluation is set to "4", and if the degree of variation of the index value is in the range of "41 to 60", the score of the 5-grade evaluation is set to "3". Further, the index normalization unit 58 sets the score of the 5-grade evaluation to "2" if the degree of variation of the index value is in the range of "61 to 80", and the degree of variation of the index value is in the range of "81 to 100". If there is, the score of the 5-grade evaluation is set to "1".

In this way, the index normalization unit 58 can lower the score for an index with a large degree of variation and increase the score for an index with a small degree of variation. In the following, a score indicating variation in index values may be referred to as a variation score.

The radar chart generation unit 59 includes a variation score of each index determined by the index normalization unit 58, and a factor score for each index of a plurality of factor candidates included in the learning information acquired by the information acquisition unit 52. Generate a radar chart based on. Such a radar chart can represent the balance between each index.

The radar chart generation unit 59 generates a radar chart for each energy management device 10B, but it is also possible to generate one radar chart for a plurality of energy management devices 10B.

The radar chart generation unit 59 transmits the generated radar chart information to the mobile terminal 60 or the energy management device 10B that has transmitted the learning information via the communication unit 51. When the mobile terminal 60 acquires the radar chart information from the server 50A, the mobile terminal 60 displays the radar chart on a display unit (not shown). Further, when the processing unit 11B of the energy management device 10B that has transmitted the learning information acquires the radar chart information from the server 50A, the display unit 13 displays the radar chart.

FIG. 26 is a diagram showing an example of a radar chart displayed on the display unit of the mobile terminal according to the fourth embodiment, and FIG. 27 is a radar chart displayed on the display unit of the mobile terminal according to the fourth embodiment. It is a figure which shows another example. The radar chart 80 shown in FIG. 26 is, for example, _{the diagnosis result of the energy management device 10B 1} , and the radar chart 81 shown in FIG. 27 is, for example, the diagnosis result of the _{energy management device 10B 2.}

The radar charts 80 and 81 show the degree of variation in the index values for each of the first index, the second index, the third index, the fourth index, and the fifth index, and the top ranks having a high improvement effect on production. Two factors are shown. In these

radar charts

80 and 81, the numbers "1, 2, 3, 4, 5" at each vertex indicate the type of index, and the alphabet "a, b, c, d, e, f," of each vertex. “G” indicates the top two factors with high improvement effects. The top two factors with high improvement effects are the top two factors among the multiple factors of energy consumption that do not contribute to production for each index.

As shown in FIG. 26, in the radar chart 80, the first index has a score of "4", the top two factors having a high improvement effect are "a" and "c", and the second index is. , The score is "2", the top two factors with high improvement effect are "b" and "c", and the third index is the score with "5", the top two factors with high improvement effect. Are "a" and "b". Further, in the radar chart 81, the fourth index has a score of "4", the top two factors having a high improvement effect are "d" and "e", and the fifth index has a score of "3". The top two factors with high improvement effects are "d" and "f".

As shown in FIG. 27, in the radar chart 81, the first index has a score of "4", the top two factors having a high improvement effect are "c" and "g", and the second index is. , The score is "5", the top two factors with high improvement effect are "d" and "e", and the third index is the score with "4", the top two factors with high improvement effect. Are "a" and "c". Further, in the radar chart 80, the fourth index has a score of "4", the top two factors having a high improvement effect are "d" and "f", and the fifth index has a score of "3". , And the top two factors with high improvement effects are "f" and "g".

Therefore, the user can grasp at a glance the top two factors having a high improvement effect for each index by the radar charts 80 and 81. Further, the user can intuitively and easily grasp the index having a large degree of variation by the radar charts 80 and 81. For example, the user can intuitively and easily grasp that the index having the largest degree of variation is the second index by the radar chart 80, and the index having the largest degree of variation is the fifth index by the radar chart 81. Can be grasped intuitively and easily.

As described above, in the energy management system 200A, the information of the radar charts 80 and 81 can be generated by the server 50A, and the information of the radar charts 80 and 81 is displayed on the mobile terminal 60 or the energy management device 10B. Therefore, the user can intuitively know the index having a large room for improvement, and can effectively utilize it by examining the improvement activity for the energy loss.

Here, it will be explained that there is room for improvement when the degree of variation in the index value is large. In the case of the first index value "time T1 from when the production equipment 2 is turned on until the production of the production equipment 2 is started", if the work procedure and the like are constant, the degree of variation in the time T1 is small. However, when there is a large variation in the work procedure or the like, the degree of variation in the time T1 becomes large, and it is presumed that there is room for improvement because some factor such as the day of the week or the person in charge is involved.

Then, it is estimated that the greater the variation in time T1, the greater the variation in work procedures, etc., and the greater the room for improvement. This is not limited to the first index value, and the same applies to the second index value, the third index value, the fourth index value, the fifth index value, and the like.

Note that the index normalization unit 58 can also determine the degree of variation of each index value by an algorithm for determining variation other than the above equation (3). For example, the index normalization unit 58 can determine the degree of variation of each index value by using the usual variance σ or other methods. As an evaluation method of the degree of variation of each index value by the index normalization unit 58, an evaluation method that can easily present room for improvement to the user according to the degree of dispersion of the index value collected from each facility is appropriately adopted. ..

The factor estimation unit 53A uses one or more types of index values normalized by the index normalization unit 58 in each of the learning process and the inference process, and the factor estimation unit 53A uses one or more types of index values that are not normalized. Different from part 53. The factor estimation unit 53A is different from the factor estimation unit 53 according to the third embodiment in that the model generation unit 55A and the inference unit 56A are provided in place of the model generation unit 55 and the inference unit 56.

The model generation unit 55A performs learning using one or more types of first normalization index values in which the input index values are normalized by the index normalization unit 58 instead of the input index values included in the learning information. It differs from the model generation unit 55 in that it performs and generates the trained model 57.

The trained model 57 generated by the model generation unit 55A is a model in which input index values based on one or more types of first normalized index values are input and factor scores of a plurality of factor candidates are output. For one or more types of the first normalized index value, for example, each of the first index value, the second index value, the third index value, the fourth index value, and the fifth index value is normalized. It is a value averaged over the sampling period. The input index value may be an integrated index value in which a plurality of types of index values are combined, instead of the average value of each of the plurality of types of index values.

The inference unit 56A replaces one or more types of index values included in the diagnosis target information with one or more types of second normalization index values in which the one or more types of index values are normalized by the index normalization unit 58. Information is input to the trained model 57. For one or more types of the second normalized index value, for example, each of the first index value, the second index value, the third index value, the fourth index value, and the fifth index value is normalized. It is a value averaged over the sampling period. Similar to the inference unit 56, the inference unit 56A determines information on two or more factor candidates having a higher factor score output from the learned model 57 among the plurality of factor candidates.

As described above, since the server 50A includes the index normalization unit 58 that normalizes one or more types of index values, the characteristics or usage status of the equipment to be diagnosed may differ in the plurality of energy management devices 10B. However, it is possible to compare the distributions or units of index values having different possible ranges among the plurality of energy management devices 10B on the same scale.

Next, the processing by the server 50A will be described using a flowchart. FIG. 28 is a flowchart showing an example of the learning process by the server according to the fourth embodiment. The processes of steps S90 and S93 of FIG. 28 are the processes of steps S60 and S62 shown in FIG. 20, and the description thereof will be omitted.

As shown in FIG. 28, the index normalization unit 58 of the server 50A normalizes one or more types of index values indicated by the learning information acquired in step S90 after the processing of step S90 is completed. Normalization processing is performed (step S91). The model generation unit 55A learns based on the sampling period and label information included in the learning information acquired by the information acquisition unit 52 and the information of one or more types of index values normalized by the index normalization unit 58. A learning process for generating the completed model 57 is executed (step S92).

In the process of step S92, the model generation unit 55A uses the sampling period information and the normalized one or more kinds of index value information as input information and the information of each factor score as label information, and performs learning by so-called supervised learning. This is done to generate the trained model 57.

FIG. 29 is a flowchart showing an example of inference processing by the server according to the fourth embodiment. Since the processing of steps S100, S103, and S104 shown in FIG. 29 is the same as the processing of steps S70, S72, and S73 shown in FIG. 21, the description thereof will be omitted.

As shown in FIG. 29, the index normalization unit 58 of the server 50A performs an index value normalization process for normalizing one or more types of index values indicated by the diagnosis target information acquired by the information acquisition unit 52 (step). S101).

Next, the factor estimation unit 53A of the server 50A is stored in the information and storage unit 54 of one or more types of second normalization index values, which are one or more types of index values normalized by the index normalization unit 58. A plurality of factor scores are calculated based on the information of the trained model 57 (step S102). In the process of step S102, the factor estimation unit 53A inputs the information of the second normalization index value into the trained model 57, and a plurality of factor scores output from the trained model 57 by the calculation of the trained model 57. To get.

An example of the hardware configuration of the server 50A according to the fourth embodiment is the same as the hardware configuration of the server 50 shown in FIG. 23. The processor 201 can execute the functions of the factor estimation unit 53A, the index normalization unit 58, and the radar chart generation unit 59 by reading and executing the program stored in the memory 202.

As described above, the server 50A according to the fourth embodiment includes an index normalization unit 58 and a radar chart generation unit 59. The index normalization unit 58 calculates the degree of variation of a plurality of types of index values indicated by the learning information for each type of index value. The radar chart generation unit 59 generates radar chart information showing the relationship between the degree of variation of each of the plurality of types of index values calculated by the index normalization unit 58 and the top two or more factor candidates. As a result, the server 50A can present information to the user so that the degree of mutual influence between the indexes can be intuitively grasped.

Further, the server 50A includes an index normalization unit 58. The index normalization unit 58 normalizes one or more types of index values. The model generation unit 55A generates the trained model 57 based on the information of the factor score and the information of one or more kinds of index values normalized by the index normalization unit 58. The inference unit 56A inputs information on one or more types of index values normalized by the index normalization unit 58 into the trained model 57, and based on the information output from the trained model 57, a plurality of factor candidates Determine the top two or more factor candidates. As a result, the server 50A distributes index values having different possible ranges among the plurality of energy management devices 10B even if the features or usage conditions of the equipment to be diagnosed differ among the plurality of energy management devices 10B. Units can be compared on the same scale.

The

processing units

11, 11A, and 11B of the

energy management devices

10, 10A, and 10B specify the index value and the factor candidate on a daily basis, but specify the index value and the factor candidate on a time zone basis, a weekly basis, a monthly unit, and the like. You can also do it. Further, the

processing units

11, 11A and 11B can also calculate the score of each factor candidate using an index of a type other than the above-mentioned index, and each factor uses only a part of the above-mentioned plurality of indexes. Candidate scores can also be calculated. In addition, the

processing units

11, 11A, and 11B can calculate the scores of factor candidates other than the above-mentioned factor candidates, and can also calculate only the scores of some of the above-mentioned plurality of factor candidates. ..

Further, the

energy management devices

10, 10A and 10B may be composed of a plurality of devices arranged at different positions from each other. For example, the

energy management devices

10, 10A, and 10B may be configured to include a collecting device and a processing device. The collecting device collects information from the

power sensors

4 and 5, the production amount sensor 6, the environment sensor 7, and the production control device 8. The processing device outputs at least a part of the ranking information based on the information collected by the collecting device. In this case, the collecting device may be configured by, for example, a PLC (Programmable Logic Controller), a data logger, or the like, and the processing device may be configured by, for example, a cloud server or a mobile terminal. The collecting device and the processing device are connected wirelessly or by wire so as to be able to communicate with each other.

Further, the

energy management devices

10, 10A and 10B may be configured to have the functions of the

servers

50 and 50A. For example, the

energy management devices

10B ₁ and 10B ₂ may include a part or all of the information acquisition unit 52, the

factor estimation unit

53, 53A, the index normalization unit 58, and the radar chart generation unit 59. good.

The configuration shown in the above embodiments is an example, and can be combined with another known technique, can be combined with each other, and does not deviate from the gist. It is also possible to omit or change a part of the configuration.

1 Production facility, 2 Production equipment, 3 Related equipment, 4, 5 Power sensor, 6 Production volume sensor, 7 Environmental sensor, 8 Production control device, 10, 10A, 10B, 10B ₁ , 10B ₂ , 10B ₃ Energy management device, 11, 11A, 11B Processing unit, 12 Production-related information storage unit, 13 Display unit, 14 Input unit, 15 Contribution information storage unit, 16,51 Communication unit, 21 Information collection unit, 22 Information generation unit, 23 Index value calculation Unit, 24 score calculation unit, 25, 25A, 25B information provision unit, 26 contribution estimation unit, 41, 41A ranking information generation unit, 42, 42A display processing unit, 50, 50A server, 52 information acquisition unit, 53, 53A Factor estimation unit, 54 storage unit, 55,55A model generation unit, 56,56A inference unit, 57 trained model, 58 index normalization unit, 59 radar chart generation unit, 60 mobile terminals, 80,81 radar chart, 200, 200A energy management system.

Claims

An index value calculation unit that calculates one or more types of index values related to energy consumption in a diagnostic target including production equipment based on production-related information that is information related to past production.
Based on the one or more kinds of index values calculated by the index value calculation unit, the energy consumption of each of the plurality of factor candidates that are candidates for the energy consumption factors that did not contribute to the production did not contribute to the production. A score calculation unit that calculates a score that indicates the degree of influence on
An energy management device including an information providing unit that outputs information of two or more factor candidates having a higher score calculated by the score calculation unit among the plurality of factor candidates.
The diagnosis target is
Includes related equipment used in connection with the production equipment
The production-related information includes
Information indicating the energy consumption of the production equipment, information indicating the energy consumption of the related equipment, and information indicating the production amount of the production equipment are included.
The index value calculation unit
A claim characterized in that one or more kinds of index values are calculated based on the information indicating the energy consumption of the production equipment, the information indicating the energy consumption of the related equipment, and the information indicating the production amount of the production equipment. Item 1. The energy management device according to item 1.
The index value of one or more types is
The first index value indicating the time from when the production facility is turned on to when the production of the production facility is started, and the time from the end of production by the production facility to when the production facility is turned off. The second index value shown, the third index value indicating the difference between the time when the related equipment is on and the time when the production equipment is on, and the production by the production equipment during the time when the production equipment is on. It is characterized by including at least one of a fourth index value indicating the ratio of time during which the production is performed and a fifth index value indicating the energy consumption of the diagnosis target per unit production amount by the production facility. The energy management device according to claim 2.
An information generation unit that generates information on the plurality of factor candidates based on the production-related information is provided.
The score calculation unit
A claim characterized in that the score is calculated based on the one or more types of index values calculated by the index value calculation unit and the information of the plurality of factor candidates generated by the information generation unit. The energy management device according to any one of 1 to 3.
The plurality of factor candidates are
Of the day, week, and month of the day, week, and month when the goods were produced by the production equipment, the person in charge of the production, the type of goods produced by the production equipment, the error occurred in the production equipment, and the environment of the production equipment. The energy management device according to any one of claims 1 to 4, wherein the energy management device includes two or more.
The one or more types of index values are a plurality of types of index values.
The score calculation unit
The scores of each of the plurality of factor candidates are calculated for each of the plurality of types of index values, and the scores are calculated.
The information providing department
The present invention according to any one of claims 1 to 5, wherein for each of the plurality of types of index values, information on two or more factor candidates having the highest score among the plurality of factor candidates is output. Energy management device.
It is provided with a contribution estimation unit that estimates the contribution of each of the plurality of factor candidates to the user's improvement activities for energy consumption that does not contribute to production.
The information providing department
Based on the contribution of each of the plurality of factor candidates estimated by the contribution estimation unit, the scores of the corresponding factor candidates among the plurality of factor candidates are corrected, and the corrected scores are the top two. The energy management device according to any one of claims 1 to 6, wherein the information of the above factor candidates is generated.
The information providing department
A claim characterized in that ranking information representing a preset number of factor candidates having a higher score among the plurality of factor candidates in the form of a ranking table is output as information of the two or more factor candidates. Item 4. The energy management device according to any one of Items 1 to 7.
Learning including the information of the one or more kinds of index values output from the energy management device according to any one of claims 1 to 8 and the information of the factor score which is the score of each of the plurality of factor candidates. A server including a model generation unit that generates a trained model that inputs information on one or more types of index values and outputs a plurality of factor scores based on the information.
The information of one or more kinds of index values regarding the energy consumption in the diagnosis target of another energy management device different from the energy management device is input to the trained model, and based on the information output from the trained model, the said The server according to claim 9, further comprising an inference unit that determines two or more higher-order factor candidates among a plurality of factor candidates.
An index normalization unit that calculates the degree of variation of a plurality of types of the index values for each type of the index value,
It is provided with a radar chart generation unit that generates radar chart information indicating the relationship between the degree of variation of each of the plurality of types of the index values calculated by the index normalization unit and the upper two or more factor candidates. The server according to claim 10.
It is equipped with an index normalization unit that normalizes one or more of the above index values.
The model generator
The trained model is generated based on the information of the factor score and the information of one or more kinds of index values normalized by the index normalization unit.
The inference unit
Information on one or more types of index values normalized by the index normalization unit is input to the trained model, and based on the information output from the trained model, the top two of the plurality of factor candidates. The server according to claim 10, wherein the above factor candidates are determined.
Any one of claims 10 to 12, comprising a communication unit that transmits information of the upper two or more factor candidates determined by the inference unit to the other energy management device or the external device. The server described in.
An index value calculation unit that calculates one or more types of index values related to energy consumption in a diagnostic target including production equipment based on production-related information that is information related to past production.
Based on the one or more kinds of index values calculated by the index value calculation unit, the energy consumption of each of the plurality of factor candidates that are candidates for the energy consumption factors that did not contribute to the production did not contribute to the production. A score calculation unit that calculates a score that indicates the degree of influence on
Based on the learning information including the information of the one or more types of index values and the information of the factor score which is the score of each of the plurality of factor candidates, the information of the one or more types of index values is input as a plurality of information. An energy management system including a model generation unit that generates a trained model that outputs the factor score.
It ’s an energy management method that a computer uses.
An index value calculation step that calculates one or more types of index values related to energy consumption in a diagnostic target including production equipment based on production-related information that is information related to past production.
Based on the one or more kinds of index values calculated by the index value calculation step, the energy consumption of each of the plurality of factor candidates that are candidates for the energy consumption factors that did not contribute to the production did not contribute to the production. A score calculation step that calculates a score that indicates the degree of influence on
An energy management method comprising: an output processing step for outputting information of two or more factor candidates having a higher score calculated by the score calculation step among the plurality of factor candidates.
An index value calculation step that calculates one or more types of index values related to energy consumption in a diagnostic target including production equipment based on production-related information that is information related to past production.
Based on the one or more kinds of index values calculated by the index value calculation step, the energy consumption of each of the plurality of factor candidates that are candidates for the energy consumption factors that did not contribute to the production did not contribute to the production. A score calculation step that calculates a score that indicates the degree of influence on
An energy management program comprising causing a computer to execute an output processing step for outputting information of two or more factor candidates having a higher score calculated by the score calculation step among the plurality of factor candidates.